Log in

Relevant bibliographies by topics / Query Prompts / Journal articles

To see the other types of publications on this topic, follow the link: Query Prompts.

Journal articles on the topic 'Query Prompts'

Author: Grafiati

Published: 2 June 2025

Last updated: 31 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Query Prompts.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Delgado-Solorzano, Cecilia, Elias Tzoc, Suzanne Rook, Christopher Vinson, and Carlos Toxtli. "A Study of LLM-Powered Student Query Support." Avances en Interacción Humano-Computadora 9, no. 1 (2024): 21–25. https://doi.org/10.47756/aihc.y9i1.141.

Full text

Abstract:

In this paper, we explore the use of Large Language Models (LLMs) to help students improve their information-seeking skills while encouraging the use of references to aid library literacy efforts. This study aims to expand the reach of library support by introducing an approach that leverages the capabilities of LLMs and well-structured prompts. Our approach begins with surveying the current changes students have faced in the last two years concerning their study habits and how they search for information. We subsequently propose a multi-step system prompt, referred as prompting architecture,

APA, Harvard, Vancouver, ISO, and other styles

2

Slifkin, Lawrence, and Marilyn Vogel. "Lubrication Article Prompts Suggestion and Suggestive Query." Physics Today 52, no. 11 (1999): 82. http://dx.doi.org/10.1063/1.882889.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Zhang, Qinye. "PromptCraft-RAG: Context-based Prompt Enhancement of Refining Query for Retrieval Augmented Generation." Applied and Computational Engineering 154, no. 1 (2025): 137–44. https://doi.org/10.54254/2755-2721/2025.tj23129.

Full text

Abstract:

Retrieval-augmented generation (RAG) has become a transformative framework in Natural Language Processing (NLP). It contributes to the generation process by retrieving relevant information from external knowledge bases, thus making the responses more accurate and contextualized. Recent developments in RAG have renewed interest in optimizing RAG frameworks, such as improving the efficiency of the retrieval module, query reconstruction, refinement, ranking mechanisms, and resolution of hallucinations. However, RAG still faces significant bottlenecks, especially when it comes to understanding kno

APA, Harvard, Vancouver, ISO, and other styles

4

Jiang, Zhengbao, Frank F. Xu, Jun Araki, and Graham Neubig. "How Can We Know What Language Models Know?" Transactions of the Association for Computational Linguistics 8 (July 2020): 423–38. http://dx.doi.org/10.1162/tacl_a_00324.

Full text

Abstract:

Recent work has presented intriguing results examining the knowledge contained in language models (LMs) by having the LM fill in the blanks of prompts such as “ Obama is a __ by profession”. These prompts are usually manually created, and quite possibly sub-optimal; another prompt such as “ Obama worked as a __ ” may result in more accurately predicting the correct profession. Because of this, given an inappropriate prompt, we might fail to retrieve facts that the LM does know, and thus any given prompt only provides a lower bound estimate of the knowledge contained in an LM. In this paper, we

APA, Harvard, Vancouver, ISO, and other styles

5

Choi, Jaekeol. "Identifying Key Terms in Prompts for Relevance Evaluation with GPT Models." International Journal on Natural Language Computing 13, no. 2 (2024): 01–19. http://dx.doi.org/10.5121/ijnlc.2024.13201.

Full text

Abstract:

Relevance evaluation of a query and a passage is essential in Information Retrieval (IR). Recently, numerous studies have been conducted on tasks related to relevance judgment using Large Language Models (LLMs) such as GPT-4, demonstrating significant improvements. However, the efficacy of LLMs is considerably influenced by the design of the prompt. The purpose of this paper is to identify which specific terms in prompts positively or negatively impact relevance evaluation with LLMs. We employed two types of prompts: those used in previous research and generated automatically by LLMs. By compa

APA, Harvard, Vancouver, ISO, and other styles

6

Meng, Fan'an, Chaoran Cui, Hongjun Dai, and Shuai Gong. "Black-Box Test-Time Prompt Tuning for Vision-Language Models." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 6 (2025): 6099–107. https://doi.org/10.1609/aaai.v39i6.32652.

Full text

Abstract:

Test-time prompt tuning (TPT) aims to adjust the vision-language models (e.g., CLIP) with learnable prompts during the inference phase. However, previous works overlooked that pre-trained models as a service (MaaS) have become a noticeable trend due to their commercial usage and potential risk of misuse. In the context of MaaS, users can only design prompts in inputs and query the black-box vision-language models through inference APIs, rendering the previous paradigm of utilizing gradient for prompt tuning is infeasible. In this paper, we propose black-box test-time prompt tuning (B²TPT), a n

APA, Harvard, Vancouver, ISO, and other styles

7

Choi, Jaekeol. "Efficient Prompt Optimization for Relevance Evaluation via LLM-Based Confusion Matrix Feedback." Applied Sciences 15, no. 9 (2025): 5198. https://doi.org/10.3390/app15095198.

Full text

Abstract:

Evaluating query-passage relevance is a crucial task in information retrieval (IR), where the performance of large language models (LLMs) greatly depends on the quality of prompts. Current prompt optimization methods typically require multiple candidate generations or iterative refinements, resulting in significant computational overhead and limited practical applicability. In this paper, we propose a novel prompt optimization method that leverages LLM-based confusion matrix feedback to efficiently optimize prompts for the relevance evaluation task. Unlike previous approaches, our method syste

APA, Harvard, Vancouver, ISO, and other styles

8

Akram, Waseem, Yanjie Jiang, Yuxia Zhang, Haris Ali Khan, and Hui Liu. "LLM-Based Method Name Suggestion with Automatically Generated Context-Rich Prompts." Proceedings of the ACM on Software Engineering 2, FSE (2025): 779–800. https://doi.org/10.1145/3715753.

Full text

Abstract:

Accurate method naming is crucial for code readability and maintainability. However, manually creating concise and meaningful names remains a significant challenge. To this end, in this paper, we propose an approach based on Large Language Model (LLMs) to suggest method names according to function descriptions. The key of the approach is ContextCraft , an automated algorithm for generating context-rich prompts for LLM that suggests the expected method names according to the prompts. For a given query (functional description), it retrieves a few best examples whose functional descriptions have

APA, Harvard, Vancouver, ISO, and other styles

9

Hu, Xiaomeng, Pin-Yu Chen, and Tsung-Yi Ho. "Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 26 (2025): 27330–38. https://doi.org/10.1609/aaai.v39i26.34943.

Full text

Abstract:

Large Language Models (LLMs) are increasingly being integrated into services such as ChatGPT to provide responses to user queries. To mitigate potential harm and prevent misuse, there have been concerted efforts to align the LLMs with human values and legal compliance by incorporating various techniques, such as Reinforcement Learning from Human Feedback (RLHF), into the training of the LLMs. However, recent research has exposed that even aligned LLMs are susceptible to adversarial manipulations known as Jailbreak Attacks. To address this challenge, this paper proposes a method called Token Hi

APA, Harvard, Vancouver, ISO, and other styles

10

Schmidt, Douglas C., Jesse Spencer-Smith, Quchen Fu, and Jules White. "Towards a Catalog of Prompt Patterns to Enhance the Discipline of Prompt Engineering." ACM SIGAda Ada Letters 43, no. 2 (2024): 43–51. http://dx.doi.org/10.1145/3672359.3672364.

Full text

Abstract:

The rapid advent of Large Language Models (LLMs), such as ChatGPT and Claude, is revolutionizing various fields, from education and healthcare to the engineering of reliable software systems. These LLMs operate through "prompts," which are natural language inputs that users employ to query and leverage the models' capabilities. Given the novelty of LLMs, the understanding of how to effectively use prompts remains largely anecdotal, based on isolated use cases. This fragmented approach limits the reliability and utility of LLMs, especially when they are applied in mission-critical software envi

APA, Harvard, Vancouver, ISO, and other styles

11

Prasannakumar, C. V., and Venifa Mini G. Dr. "Imperative Methodologies of Query Optimization in Large Language Models." Advanced Innovations in Computer Programming Languages 7, no. 2 (2025): 33–38. https://doi.org/10.5281/zenodo.15402629.

Full text

Abstract:

<em>The improved and spontaneous development of large language models (LLMs) has transformed various applications, from natural language processing models to complex problem- solving applications. To enhance the applications SQL based query prompts are being given to the system, hence the most optimized queries may ameliorate the performance. Query optimization will enhance the prompt inputs and will pick up the full potential of these models to an extent. But some situations some of the basic constrains pull back the result and the resulted speed remains a critical challenge. This paper explo

APA, Harvard, Vancouver, ISO, and other styles

12

Brahmavar, Shreyas Bhat, Ashwin Srinivasan, Tirtharaj Dash, et al. "Generating Novel Leads for Drug Discovery Using LLMs with Logical Feedback." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 1 (2024): 21–29. http://dx.doi.org/10.1609/aaai.v38i1.27751.

Full text

Abstract:

Large Language Models (LLMs) can be used as repositories of biological and chemical information to generate pharmacological lead compounds. However, for LLMs to focus on specific drug targets typically requires experimentation with progressively more refined prompts. Results thus become dependent not just on what is known about the target, but also on what is known about the prompt- engineering. In this paper, we separate the prompt into domain-constraints that can be written in a standard logical form and a simple text-based query. We investigate whether LLMs can be guided, not by refining pr

APA, Harvard, Vancouver, ISO, and other styles

13

Peng, Shi-Feng, Guolei Sun, Yong Li, Hongsong Wang, and Guo-Sen Xie. "SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 6 (2025): 6488–96. https://doi.org/10.1609/aaai.v39i6.32695.

Full text

Abstract:

The primary challenge of cross-domain few-shot segmentation (CD-FSS) is the domain disparity between the training and inference phases, which can exist in either the input data or the target classes. Previous models struggle to learn feature representations that generalize to various unknown domains from limited training domain samples. In contrast, the large-scale visual model SAM, pre-trained on tens of millions of images from various domains and classes, possesses excellent generalizability. In this work, we propose a SAM-aware graph prompt reasoning network (GPRN) that fully leverages SAM

APA, Harvard, Vancouver, ISO, and other styles

14

Hernandez-Camero, Ines-Virginia, Eva Garcia-Lopez, Antonio Garcia-Cabot, and Sergio Caro-Alvaro. "Context-Aware Few-Shot Learning SPARQL Query Generation from Natural Language on an Aviation Knowledge Graph." Machine Learning and Knowledge Extraction 7, no. 2 (2025): 52. https://doi.org/10.3390/make7020052.

Full text

Abstract:

Question answering over domain-specific knowledge graphs implies several challenges. It requires sufficient knowledge of the world and the domain to understand what is being asked, familiarity with the knowledge graph’s structure to build a correct query, and knowledge of the query language. However, mastering all of these is a time-consuming task. This work proposes a prompt-based approach that enables natural language to generate SPARQL queries. By leveraging the advanced language capabilities of large language models (LLMs), we constructed prompts that include a natural-language question, r

APA, Harvard, Vancouver, ISO, and other styles

15

Gopu, Venkata Rama Muni Kumar, and Madhavi Dunna. "Unsupervised Content Mining in CBIR: Harnessing Latent Diffusion for Complex Text-Based Query Interpretation." Journal of Imaging 10, no. 6 (2024): 139. http://dx.doi.org/10.3390/jimaging10060139.

Full text

Abstract:

The paper demonstrates a novel methodology for Content-Based Image Retrieval (CBIR), which shifts the focus from conventional domain-specific image queries to more complex text-based query processing. Latent diffusion models are employed to interpret complex textual prompts and address the requirements of effectively interpreting the complex textual query. Latent Diffusion models successfully transform complex textual queries into visually engaging representations, establishing a seamless connection between textual descriptions and visual content. Custom triplet network design is at the heart

APA, Harvard, Vancouver, ISO, and other styles

16

Choi, Jaekeol. "Binary or Graded, Few-Shot or Zero-Shot: Prompt Design for GPTs in Relevance Evaluation." Advances in Artificial Intelligence and Machine Learning 04, no. 03 (2024): 2687–702. http://dx.doi.org/10.54364/aaiml.2024.43156.

Full text

Abstract:

Evaluating the relevance between a query and a passage is a pivotal task in Information Retrieval (IR). Utilizing such relevance evaluations can assist in ranking as well as in the creation of datasets for training and testing. The recent advancements in Large Language Models (LLMs) like GPT-4 have contributed to performance enhancements across many natural language processing tasks. Specifically, in the IR domain, many studies are being conducted on tasks related to relevance judgment, showing notable improvements. However, the efficacy of LLMs is considerably influenced by the design of the

APA, Harvard, Vancouver, ISO, and other styles

17

Jia, Mingda, Liming Zhao, Ge Li, and Yun Zheng. "Orchestrating the Symphony of Prompt Distribution Learning for Human-Object Interaction Detection." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 4 (2025): 3940–48. https://doi.org/10.1609/aaai.v39i4.32412.

Full text

Abstract:

Human-object interaction (HOI) detectors with popular query-transformer architecture have achieved promising performance. However, accurately identifying uncommon visual patterns and distinguishing between ambiguous HOIs continue to be difficult for them. We observe that these difficulties may arise from the limited capacity of traditional detector queries to represent diverse intra-category patterns and inter-category dependencies. To address this, we introduce the Interaction Prompt Distribution Learning (InterProDa) approach. InterProDa learns multiple sets of soft prompts and estimates cat

APA, Harvard, Vancouver, ISO, and other styles

18

Zhai, Yajing, Yawen Zeng, Zhiyong Huang, Zheng Qin, Xin Jin, and Da Cao. "Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 7 (2024): 6979–87. http://dx.doi.org/10.1609/aaai.v38i7.28524.

Full text

Abstract:

The fine-grained attribute descriptions can significantly supplement the valuable semantic information for person image, which is vital to the success of person re-identification (ReID) task. However, current ReID algorithms typically failed to effectively leverage the rich contextual information available, primarily due to their reliance on simplistic and coarse utilization of image attributes. Recent advances in artificial intelligence generated content have made it possible to automatically generate plentiful fine-grained attribute descriptions and make full use of them. Thereby, this paper

APA, Harvard, Vancouver, ISO, and other styles

19

Gupta, Sudhanshu, and Krishna Kumar Tiwari. "Exploratory Search Prompt Generation using n-Degree Connection in Knowledge Graph." Asian Journal of Research in Computer Science 16, no. 4 (2023): 318–26. http://dx.doi.org/10.9734/ajrcos/2023/v16i4393.

Full text

Abstract:

Search engines play a vital role in retrieving in- formation, but users often struggle to express their precise information needs, resulting in less-than-optimal search results. Therefore, enhancing search query refinement is crucial to elevate the accuracy and relevance of search outcomes. One particular challenge that existing search engines face is presenting refined results for queries containing two or more unrelated entities. This paper presents a novel approach for efficient search prompt generation by leveraging connected nodes and attributes in the knowledge graph. We propose a

APA, Harvard, Vancouver, ISO, and other styles

20

Ferreira, Silvan, Allan Martins, Daniel G. Costa, and Ivanovitch Silva. "Integrating Textual Queries with AI-Based Object Detection: A Compositional Prompt-Guided Approach." Sensors 25, no. 7 (2025): 2258. https://doi.org/10.3390/s25072258.

Full text

Abstract:

While object detection and recognition have been extensively adopted by many applications in decision-making, new algorithms and methodologies have emerged to enhance the automatic identification of target objects. In particular, the rise of deep learning and language models has opened many possibilities in this area, although challenges in contextual query analysis and human interactions persist. This article presents a novel neuro-symbolic object detection framework that aligns object proposals with textual prompts using a deep learning module while enabling logical reasoning through a symbo

APA, Harvard, Vancouver, ISO, and other styles

21

Yang, Xiangpeng, Linchao Zhu, Xiaohan Wang, and Yi Yang. "DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 7 (2024): 6540–48. http://dx.doi.org/10.1609/aaai.v38i7.28475.

Full text

Abstract:

Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models due to increasing model size continues to pose a problem. To address this challenge, prompt tuning has emerged as an alternative. However, existing works still face two problems when adapting pretrained image-text models to downstream video-text tasks: (1) The visual encoder could only encode frame-level features and failed to extract global-level general v

APA, Harvard, Vancouver, ISO, and other styles

22

Paul, Debjyoti, Jie Cao, Feifei Li, and Vivek Srikumar. "Database workload characterization with query plan encoders." Proceedings of the VLDB Endowment 15, no. 4 (2021): 923–35. http://dx.doi.org/10.14778/3503585.3503600.

Full text

Abstract:

Smart databases are adopting artificial intelligence (AI) technologies to achieve instance optimality , and in the future, databases will come with prepackaged AI models within their core components. The reason is that every database runs on different workloads, demands specific resources, and settings to achieve optimal performance. It prompts the necessity to understand workloads running in the system along with their features comprehensively, which we dub as workload characterization. To address this workload characterization problem, we propose our query plan encoders that learn essential

APA, Harvard, Vancouver, ISO, and other styles

23

Yang, Qinghua, Yan Tian, Jing Sun, and Fangyuan He. "Enhancing Open-Set Few-Shot Object Detection with Limited Visual Prompts." Information Technology and Control 54, no. 2 (2025): 712–34. https://doi.org/10.5755/j01.itc.54.2.41078.

Full text

Abstract:

The text-prompt-based open-vocabulary object detection model effectively encapsulates the abstract concepts of common objects, thereby overcoming the limitations of pre-trained models, which are restricted to detecting a fixed, predefined set of categories. However, due to data scarcity and the constraints of textual descriptions, representing rare or complex objects solely through text remains challenging. In this study, we propose an open-set detection model that supports both visual and textual prompt queries (VTP-OD) to enhance few-shot object detection. A small number of visual prompts no

APA, Harvard, Vancouver, ISO, and other styles

24

Park, Suho, SuBeen Lee, Hyun Seok Seong, Jaejoon Yoo, and Jae-Pil Heo. "Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 6 (2025): 6425–33. https://doi.org/10.1609/aaai.v39i6.32688.

Full text

Abstract:

We propose Foreground-Covering Prototype Generation and Matching to resolve Few-Shot Segmentation (FSS), which aims to segment target regions in unlabeled query images based on labeled support images. Unlike previous research, which typically estimates target regions in the query using support prototypes and query pixels, we utilize the relationship between support and query prototypes. To achieve this, we utilize two complementary features: SAM Image Encoder features for pixel aggregation and ResNet features for class consistency. Specifically, we construct support and query prototypes with S

APA, Harvard, Vancouver, ISO, and other styles

25

Trummer, Immanuel. "Demonstrating GPT-DB: Generating Query-Specific and Customizable Code for SQL Processing with GPT-4." Proceedings of the VLDB Endowment 16, no. 12 (2023): 4098–101. http://dx.doi.org/10.14778/3611540.3611630.

Full text

Abstract:

GPT-DB generates code for SQL processing in general-purpose programming languages such as Python. Generated code can be freely customized using user-provided natural language instructions. This enables users, for instance, to try out specific libraries for SQL processing or to generate non-standard output while processing. GPT-DB is based on OpenAI's GPT model series, neural networks capable of translating natural language instructions into code. By default, GPT-DB exploits the most recently released GPT-4 model whereas visitors may also select prior versions for comparison. GPT-DB automatical

APA, Harvard, Vancouver, ISO, and other styles

26

Beurer-Kellner, Luca, Marc Fischer, and Martin Vechev. "Prompting Is Programming: A Query Language for Large Language Models." Proceedings of the ACM on Programming Languages 7, PLDI (2023): 1946–69. http://dx.doi.org/10.1145/3591300.

Full text

Abstract:

Large language models have demonstrated outstanding performance on a wide range of tasks such as question answering and code generation. On a high level, given an input, a language model can be used to automatically complete the sequence in a statistically-likely way. Based on this, users prompt these models with language instructions or examples, to implement a variety of downstream tasks. Advanced prompting methods can even imply interaction between the language model, a user, and external tools such as calculators. However, to obtain state-of-the-art performance or adapt language models for

APA, Harvard, Vancouver, ISO, and other styles

27

Zhao, Yunlong, Haoran Wu, and Bo Xu. "Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 24 (2025): 26048–56. https://doi.org/10.1609/aaai.v39i24.34800.

Full text

Abstract:

Prompt compression is increasingly studied for its potential to reduce computational costs and alleviate the burden on language models when processing lengthy prompts. Prior research has assessed token retention and removal by calculating information entropy. However, prompt compression encounters two significant challenges: (1) Information entropy, while widely used, may not be the optimal compression metric; and (2) The semantic significance of tokens is context-dependent, which renders independent token retention decisions inadequate. We posit that the solution to these challenges lies in t

APA, Harvard, Vancouver, ISO, and other styles

28

Tanković, Nikola, Robert Šajina, and Ivan Lorencin. "Transforming Medical Data Access: The Role and Challenges of Recent Language Models in SQL Query Automation." Algorithms 18, no. 3 (2025): 124. https://doi.org/10.3390/a18030124.

Full text

Abstract:

Generating accurate SQL queries from natural language is critical for enabling non-experts to interact with complex databases, particularly in high-stakes domains like healthcare. This paper presents an extensive evaluation of state-of-the-art large language models (LLM), including LLaMA 3.3, Mixtral, Gemini, Claude 3.5, GPT-4o, and Qwen for transforming medical questions into executable SQL queries using the MIMIC-3 and TREQS datasets. Our approach employs LLMs with various prompts across 1000 natural language questions. The experiments are repeated multiple times to assess performance consis

APA, Harvard, Vancouver, ISO, and other styles

29

Huang, Xin, Shilong Wang, Tong Jia, Zhihang Gou, and Jingjing Li. "Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 16 (2025): 17485–93. https://doi.org/10.1609/aaai.v39i16.33922.

Full text

Abstract:

In the era of big data, cross-modal retrieval is increasingly important in research and application. Given the latent complexity and non-intuitive nature of cross-modal relationships, leveraging external knowledge such as large models has become a popular approach to facilitate modality alignment. Existing methods typically address these challenges by fine-tuning model encoders or using a fixed number of prompts. However, these approaches struggle with the significant information asymmetry between image-text pairs and the high distribution diversity of image data. These limitations not only in

APA, Harvard, Vancouver, ISO, and other styles

30

Jin, Haibo, Haoxuan Che, Yi Lin, and Hao Chen. "PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 3 (2024): 2607–15. http://dx.doi.org/10.1609/aaai.v38i3.28038.

Full text

Abstract:

Automatic medical report generation (MRG) is of great research value as it has the potential to relieve radiologists from the heavy burden of report writing. Despite recent advancements, accurate MRG remains challenging due to the need for precise clinical understanding and disease identification. Moreover, the imbalanced distribution of diseases makes the challenge even more pronounced, as rare diseases are underrepresented in training data, making their diagnosis unreliable. To address these challenges, we propose diagnosis-driven prompts for medical report generation (PromptMRG), a novel fr

APA, Harvard, Vancouver, ISO, and other styles

31

Zhang, Jiahao, Bowen Wang, Hong Liu, Liangzhi Li, Yuta Nakashima, and Hajime Nagahara. "E-InMeMo: Enhanced Prompting for Visual In-Context Learning." Journal of Imaging 11, no. 7 (2025): 232. https://doi.org/10.3390/jimaging11070232.

Full text

Abstract:

Large-scale models trained on extensive datasets have become the standard due to their strong generalizability across diverse tasks. In-context learning (ICL), widely used in natural language processing, leverages these models by providing task-specific prompts without modifying their parameters. This paradigm is increasingly being adapted for computer vision, where models receive an input–output image pair, known as an in-context pair, alongside a query image to illustrate the desired output. However, the success of visual ICL largely hinges on the quality of these prompts. To address this, w

APA, Harvard, Vancouver, ISO, and other styles

32

Yu, En, Songtao Liu, Zhuoling Li, et al. "Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 3 (2023): 3304–12. http://dx.doi.org/10.1609/aaai.v37i3.25437.

Full text

Abstract:

Although existing multi-object tracking (MOT) algorithms have obtained competitive performance on various benchmarks, almost all of them train and validate models on the same domain. The domain generalization problem of MOT is hardly studied. To bridge this gap, we first draw the observation that the high-level information contained in natural language is domain invariant to different tracking domains. Based on this observation, we propose to introduce natural language representation into visual MOT models for boosting the domain generalization ability. However, it is infeasible to label every

APA, Harvard, Vancouver, ISO, and other styles

33

Lu, Changsheng, and Piotr Koniusz. "Detect Any Keypoints: An Efficient Light-Weight Few-Shot Keypoint Detector." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 4 (2024): 3882–90. http://dx.doi.org/10.1609/aaai.v38i4.28180.

Full text

Abstract:

Recently the prompt-based models have become popular across various language and vision tasks. Following that trend, we perform few-shot keypoint detection (FSKD) by detecting any keypoints in a query image, given the prompts formed by support images and keypoints. FSKD can be applied to detecting keypoints and poses of diverse animal species. In order to maintain flexibility of detecting varying number of keypoints, existing FSKD approaches modulate query feature map per support keypoint, then detect the corresponding keypoint from each modulated feature via a detection head. Such a separatio

APA, Harvard, Vancouver, ISO, and other styles

34

Li, Muzhi, Cehao Yang, Chengjin Xu, et al. "Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 11 (2025): 12102–11. https://doi.org/10.1609/aaai.v39i11.33318.

Full text

Abstract:

Inductive knowledge graph completion (KGC) aims to predict missing triples with unseen entities. Recent works focus on modeling reasoning paths between the head and tail entity as direct supporting evidence. However, these methods depend heavily on the existence and quality of reasoning paths, which limits their general applicability in different scenarios. In addition, we observe that latent type constraints and neighboring facts inherent in KGs are also vital in inferring missing triples. To effectively utilize all useful information in KGs, we introduce CATS, a novel context-aware inductive

APA, Harvard, Vancouver, ISO, and other styles

35

Tao, Shiyu, and Jiamin Zheng. "Leveraging Prototypical Prompt Learning for Robust Bridge Defect Classification in Civil Infrastructure." Electronics 14, no. 7 (2025): 1407. https://doi.org/10.3390/electronics14071407.

Full text

Abstract:

Despite significant advancements in bridge façade defect classification, real-world automated inspections continue to face substantial challenges, including faint defect visibility, low lighting conditions, overexposure, noise interference, motion blur, and occlusions. These factors, stemming from variable environmental conditions and unstable imaging angles, severely degrade model performance. To address this issue, we introduce the Hard Defect Classification Dataset (HDCD), which systematically incorporates these six challenging conditions. Benchmarking state-of-the-art (SOTA) methods on the

APA, Harvard, Vancouver, ISO, and other styles

36

Dæhli, Olav, Bjørn Kristoffersen, and Per Lauvås. "AI chatbot: I want help, not the answer!" European Conference on e-Learning 23, no. 1 (2024): 77–84. http://dx.doi.org/10.34190/ecel.23.1.2810.

Full text

Abstract:

In recent years, the integration of artificial intelligence (AI) into educational settings has become a topic of great interest. As technology continues to evolve, educators and students are exploring how AI can enhance learning experiences. University of South-Eastern Norway (USN) and Kristiania University College (HK) are developing a web-based educational tool, DbPersist, where IT students can practice tasks within the database subject and receive automated feedback. The latest version now also offers students suggestions on how to utilize AI for learning while they are solving various data

APA, Harvard, Vancouver, ISO, and other styles

37

Rego, G. E., and E. A. Pitukhin. "Method of Collaboration between Humans and Generative Artificial Intelligence in the Development of Information Systems." Programmnaya Ingeneria 16, no. 1 (2025): 13–27. https://doi.org/10.17587/prin.16.13-27.

Full text

Abstract:

We propose a method for information system (IS) design with a focus on the applicability of intelligent chatbots. An analysis of existing chatbots shows that current solutions do not have the ability to formulate IS requirements during designing without human intervention. The study proposes to integrate ChatGPT (GPT4 model) as a chatbot to solve the problem of writing requirements elicitation for IS. The proposed method for solving the problem is based on a gradual reduction in entropy of chatbot response, which can be achieved by controlling such basic query parameters as the form, depth and

APA, Harvard, Vancouver, ISO, and other styles

38

Zhang, Yinglun, Aryan Singh Dalal, Caleb Martin, Srikar Reddy Gadusu, and Hande Küçük McGinty. "OLIVE: Ontology Learning With Integrated Vector Embeddings." Applied Ontology 20, no. 1 (2025): 36–53. https://doi.org/10.1177/15705838251329268.

Full text

Abstract:

The traditional approach to ontology development is characterized by its labor-intensive nature, requiring extensive effort and domain expertise to define intricate structures, relationships, and concepts accurately. This study proposes a paradigm shift in ontology development by harnessing the capabilities of large language models (LLMs). This methodology entails the creation of an interactive interface that empowers users to query LLMs using prompts, facilitating the retrieval of pertinent information with ease. Subsequent analysis of this information allows for identifying key relationships

APA, Harvard, Vancouver, ISO, and other styles

39

Liu, Yuting, Jinghao Zhang, Yizhou Dang, et al. "CoRA: Collaborative Information Perception by Large Language Model’s Weights for Recommendation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 12 (2025): 12246–54. https://doi.org/10.1609/aaai.v39i12.33334.

Full text

Abstract:

Involving collaborative information in Large Language Models (LLMs) is a promising technique for adapting LLMs for recommendation. Existing methods achieve this by concatenating collaborative features with text tokens into a unified sequence input and then fine-tuning to align these features with LLM's input space. Although effective, in this work, we identify two limitations when adapting LLMs to recommendation tasks, which hinder the integration of general knowledge and collaborative information, resulting in sub-optimal recommendation performance. (1) Fine-tuning LLM with recommendation dat

APA, Harvard, Vancouver, ISO, and other styles

40

Naranjo, Jose E., Maria M. Llumiquinga, Washington D. Vaca, and Cristian X. Espin. "Generative AI vs. Traditional Databases: Insights from Industrial Engineering Applications." Publications 13, no. 2 (2025): 14. https://doi.org/10.3390/publications13020014.

Full text

Abstract:

This study evaluates the efficiency and accuracy of Generative AI (GAI) tools, specifically ChatGPT and Gemini, in comparison with traditional academic databases for industrial engineering research. It was conducted in two phases. First, a survey was administered to 101 students to assess their familiarity with GAIs and the most commonly used tools in their academic field. Second, an assessment of the quality of the information provided by GAIs was carried out, in which 11 industrial engineering professors participated as evaluators. The study focuses on the query process, response times, and

APA, Harvard, Vancouver, ISO, and other styles

41

Jannuzzi, Marcelo, Yuriy Perezhohin, Fernando Peres, Mauro Castelli, and Aleš Popovič. "Zero-Shot Prompting Strategies for Table Question Answering with a Low-Resource Language." Emerging Science Journal 8, no. 5 (2024): 2003–22. http://dx.doi.org/10.28991/esj-2024-08-05-020.

Full text

Abstract:

This work explores the application of zero-shot prompting strategies for table question answering (TQA) in Portuguese, focusing specifically on the Text2SQL task. This task involves translating questions posed in natural language into Structured Query Language (SQL) queries, which can be executed against a database to answer the original question. Given the popularity of relational databases across various domains, advancements in this field can substantially impact the accessibility and democratization of data as simpler and more intuitive interfaces for database interaction are developed. De

APA, Harvard, Vancouver, ISO, and other styles

42

Wang, Liang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. "Large Search Model: Redefining Search Stack in the Era of LLMs." ACM SIGIR Forum 57, no. 2 (2023): 1–16. http://dx.doi.org/10.1145/3642979.3643006.

Full text

Abstract:

Modern search engines are built on a stack of different components, including query understanding, retrieval, multi-stage ranking, and question answering, among others. These components are often optimized and deployed independently. In this paper, we introduce a novel conceptual framework called large search model , which redefines the conventional search stack by unifying search tasks with one large language model (LLM). All tasks are formulated as autoregressive text generation problems, allowing for the customization of tasks through the use of natural language prompts. This proposed frame

APA, Harvard, Vancouver, ISO, and other styles

43

BASHA, SAMEER. "Customer Support Automation of Ticket Creation (RPA) using UiPath." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 01 (2025): 1–9. https://doi.org/10.55041/ijsrem40769.

Full text

Abstract:

In the dynamic landscape of customer support, manual ticket creation from customer emails is a labor-intensive and error-prone process that impedes operational efficiency. This project proposes an automated system utilizing Robotic Process Automation (RPA) powered by UiPath to streamline the ticket creation process. The solution automates the extraction of critical data from emails, including customer IDs, issue descriptions, and priorities, to create tickets in Customer Relationship Management (CRM) systems. Missing information prompts automated follow-ups, ensuring query resolution. Addition

APA, Harvard, Vancouver, ISO, and other styles

44

Alexeeva, L. G., and P. S. Alexeev. "Prompt Language, or Features of Formulation of Queries to Generative Neural Networks for Image Creation." Verba Northwest Linguistic Journal, no. 3 (2024): 50–61. https://doi.org/10.34680/verba-2024-3(13)-50-61.

Full text

Abstract:

The article deals with the problem of formulating a competent request (prompt) to generative neural networks that allow to create an image. This topic is currently very relevant, because due to the rapid development of technological progress, artificial intelligence systems are being implemented in almost all areas of human life. Many users do not know how to properly make a request to a generative neural network, so the result is often inaccurate or even incorrect. In the course of the research, an experiment was conducted, in which 67 students of NovSU Polytechnic College, majoring in Inform

APA, Harvard, Vancouver, ISO, and other styles

45

Wu, Yi-Chao, Zhen-Di Shao, and Hsuan-Kai Kao. "Wearable Device for Residential Elbow Joint Rehabilitation with Voice Prompts and Tracking Feedback APP." Applied Sciences 11, no. 21 (2021): 10225. http://dx.doi.org/10.3390/app112110225.

Full text

Abstract:

In this paper, we propose a wearable device for residential elbow joint rehabilitation with voice prompts and a tracking feedback app (WDRTFAPP). We have developed the app as well as the Arduino embedded system, which we have integrated together. In this research, the patients were simulated by our team not real patients. By using this wearable device, the elbow joint rehabilitation could be executed at home for the simulated patients with mild and moderately mild elbow joint symptoms. During the rehabilitation, data captured by the wearable device were sent to the tracking feedback APP, using

APA, Harvard, Vancouver, ISO, and other styles

46

Grebeniuk, D. I., I. V. Taran, and O. A. Nazarchuk. "Intravaginal use of clindamycin phosphate in therapy of bacterial vaginosis: peculiarities of pharmacokinetics depending on the level of hydrogen sulfide in the organism (literature review)." Reports of Vinnytsia National Medical University 24, no. 4 (2020): 726–31. http://dx.doi.org/10.31393/reports-vnmedical-2020-24(4)-29.

Full text

Abstract:

Annotation. The article provides an overview of modern literature data on the problems of bacterial vaginosis, its therapy with clindamycin, the pharmacokinetics of this pharmacological drug, and the potential effect of the background level of hydrogen sulfide in the body on the pharmacokinetics of drugs. From PubMed, ScienceDirect, UpToDate databases, 50 sources were selected that met the conditions of the query: the latest publications (for the last 5 years), or the latest publications on this issue (regardless of age). The wide and diverse influence of endogenous hydrogen sulfide on the cou

APA, Harvard, Vancouver, ISO, and other styles

47

Borthick, A. Faye, and Lucia N. Smeal. "Data Analytics in Tax Research: Analyzing Worker Agreements and Compensation Data to Distinguish Between Independent Contractors and Employees Using IRS Factors." Issues in Accounting Education 35, no. 3 (2020): 1–23. http://dx.doi.org/10.2308/issues-18-061.

Full text

Abstract:

ABSTRACT This case prompts learners to analyze compensation data and worker agreements to assess a company's likely compliance with requirements for classifying workers as independent contractors rather than employees based on the factors the Internal Revenue Service (IRS) uses for compliance with IRS Rev. Rul. 87-41 and Treas. Reg. § 31.3401(c)-1. Students combine tax research and data analysis to identify risky employment practices, recommend corrective action to bring the company into compliance, and estimate potential penalties if the IRS were to declare the company not in compliance. Stud

APA, Harvard, Vancouver, ISO, and other styles

48

Viswanathan, Vijay, Kiril Gashteovski, Kiril Gashteovski, Carolin Lawrence, Tongshuang Wu, and Graham Neubig. "Large Language Models Enable Few-Shot Clustering." Transactions of the Association for Computational Linguistics 12 (2024): 321–33. http://dx.doi.org/10.1162/tacl_a_00648.

Full text

Abstract:

Abstract Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the user’s intent. Existing approaches to semi-supervised clustering require a significant amount of feedback from an expert to improve the clusters. In this paper, we ask whether a large language model (LLM) can amplify an expert’s guidance to enable query-efficient, few-shot semi-supervised text clustering. We show that LLMs are surprisingly effective at improving clustering. We explore three stages where LLMs

APA, Harvard, Vancouver, ISO, and other styles

49

TREMBLAY, JEAN-THOMAS. "On Feeling Political: Negotiating (within) Affective Landscapes and Soundscapes." PhaenEx 7, no. 2 (2012): 96. http://dx.doi.org/10.22329/p.v7i2.3570.

Full text

Abstract:

This article generates an affective hermeneutics of the political. The research question, What is feeling political? is, at first, refined through the oeuvre of political theorist Simone Weil, whose focus on experience, involvement and attention highlights the role of sentience in political life. The inescapable normativity of Weil’s texts calls for an alternative approach to the question at hand, one that acknowledges the inevitability of the phenomenon of feeling political. In order to produce such an approach, the realm in which said phenomenon occurs is spatialized as an indefinite series

APA, Harvard, Vancouver, ISO, and other styles

50

Yao, Jiarui, Zinaida Perova, Tushar Mandloi, Elizabeth Lewis, Helen Parkinson, and Guergana Savova. "Extracting Knowledge From Scientific Texts on Patient-Derived Cancer Models Using Large Language Models: Algorithm Development and Validation Study." JMIR Bioinformatics and Biotechnology 6 (June 30, 2025): e70706-e70706. https://doi.org/10.2196/70706.

Full text

Abstract:

Abstract Background Patient-derived cancer models (PDCMs) have become essential tools in cancer research and preclinical studies. Consequently, the number of publications on PDCMs has increased significantly over the past decade. Advances in artificial intelligence, particularly in large language models (LLMs), offer promising solutions for extracting knowledge from scientific literature at scale. Objective This study aims to investigate LLM-based systems, focusing specifically on prompting techniques for the automated extraction of PDCM-related entities from scientific texts. Methods We explo

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!