语言大模型 / LLM - arXivDaily 专题

2412.16933 2024-12-24 cs.IR cs.AI cs.CL 82%

Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Models

Kai Zheng, Qingfeng Sun, Can Xu, Peng Yu, Qingwei Guo

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 13 pages, 5 figures

2412.11453 2024-12-17 cs.CL cs.AI 82%

ACE-$M^3$: Automatic Capability Evaluator for Multimodal Medical Models

Xiechi Zhang, Shunfan Zheng, Linlin Wang, Gerard de Melo, Zhu Cao, Xiaoling Wang, Liang He

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；preference optimization(abstract)

2310.12902 2024-11-05 cs.CL cs.AI 82%

Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling

Nina Begus

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Journal ref Humanities and Social Sciences Communications 11: 1392 (2024)

2406.05794 2024-10-25 cs.CL cs.AI 82%

RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation

Kiseung Kim, Jay-Yoon Lee

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；SLM(abstract)

2410.12848 2024-10-18 cs.CL cs.AI cs.HC 82%

Prompt Engineering a Schizophrenia Chatbot: Utilizing a Multi-Agent Approach for Enhanced Compliance with Prompt Instructions

Per Niklas Waaler, Musarrat Hussain, Igor Molchanov, Lars Ailo Bongo, Brita Elvevåg

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2410.05361 2024-10-10 cs.LG cs.AI cs.SD eess.AS 82%

RespLLM: Unifying Audio and Text with Multimodal LLMs for Generalized Respiratory Health Prediction

Yuwei Zhang, Tong Xia, Aaqib Saeed, Cecilia Mascolo

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

2410.02721 2024-10-04 cs.CL cs.AI cs.IR cs.SE 82%

Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization

Ryan C. Barron, Ves Grantcharov, Selma Wanna, Maksim E. Eren, Manish Bhattarai, Nicholas Solovyev, George Tompkins, Charles Nicholas, Kim Ø. Rasmussen, Cynthia Matuszek, Boian S. Alexandrov

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 9 pages 7 figures, 1 table, 1 cypher code Accepted to ICMLA 2024

2409.06433 2024-09-11 cs.DL cs.CL cs.LG 82%

Fine-tuning and Prompt Engineering with Cognitive Knowledge Graphs for Scholarly Knowledge Organization

Gollam Rabby, Sören Auer, Jennifer D'Souza, Allard Oelen

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2409.02530 2024-09-05 cs.LG cs.AI 82%

Understanding eGFR Trajectories and Kidney Function Decline via Large Multimodal Models

Chih-Yuan Li, Jun-Ting Wu, Chan Hsu, Ming-Yen Lin, Yihuang Kang

专题命中领域大模型：large language model(abstract)；language model(abstract)；foundation model(abstract)；prompting(abstract)

Comments This preprint version includes corrections of typographical errors related to numerical values in Table 2, which were present in the version published at the BDH workshop in MIPR 2024. These corrections do not affect the overall conclusions of the study

2408.12055 2024-08-23 cs.CL cs.LG 82%

Aligning (Medical) LLMs for (Counterfactual) Fairness

Raphael Poulain, Hamed Fayyaz, Rahmatollah Beheshti

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；preference optimization(abstract)

Comments arXiv admin note: substantial text overlap with arXiv:2404.15149

2404.15149 2024-04-24 cs.CL cs.LG 82%

Bias patterns in the application of LLMs for clinical decision support: A comprehensive study

Raphael Poulain, Hamed Fayyaz, Rahmatollah Beheshti

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2402.05125 2024-04-11 cs.CL cs.AI 82%

Zero-Shot Clinical Trial Patient Matching with LLMs

Michael Wornow, Alejandro Lozano, Dev Dash, Jenelle Jindal, Kenneth W. Mahaffey, Nigam H. Shah

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2403.08664 2024-03-15 cs.CL cs.LG 82%

Zero-shot and Few-shot Generation Strategies for Artificial Clinical Records

Erlend Frayling, Jake Lever, Graham McDonald

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 4 pages

2402.01828 2024-02-08 cs.CL cs.AI cs.SD eess.AS 82%

Retrieval Augmented End-to-End Spoken Dialog Models

Mingqiu Wang, Izhak Shafran, Hagen Soltau, Wei Han, Yuan Cao, Dian Yu, Laurent El Shafey

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；SLM(abstract)

Journal ref Proc. ICASSP 2024

2312.14345 2024-01-19 cs.AI cs.CL cs.HC 82%

Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs

Behnam Rahdari, Hao Ding, Ziwei Fan, Yifei Ma, Zhuotong Chen, Anoop Deoras, Branislav Kveton

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments The 17th ACM International Conference on Web Search and Data Mining (WSDM 2024)

2310.14393 2023-10-24 cs.CL cs.AI 82%

Merging Generated and Retrieved Knowledge for Open-Domain QA

Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments EMNLP 2023 - Camera Ready

2309.08827 2023-09-19 cs.CL cs.AI 82%

S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs

Sarkar Snigdha Sarathi Das, Chirag Shah, Mengting Wan, Jennifer Neville, Longqi Yang, Reid Andersen, Georg Buscher, Tara Safavi

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2212.02199 2022-12-06 cs.CL cs.AI 82%

Legal Prompt Engineering for Multilingual Legal Judgement Prediction

Dietrich Trautmann, Alina Petrova, Frank Schilder

专题命中领域大模型：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2606.28410 2026-06-30 cs.CV cs.AI 82%

RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation

RSGPNet：遥感开放词汇语义分割的几何提示

Shanwen Wang, Xin Sun, Sirui Wang, Xiao Xiang Zhu

专题命中领域大模型：prompting(title,abstract)；分类 cs.AI；large language model(comments)；language model(comments)

AI总结提出RSGPNet，一种无需训练的几何提示框架，通过对象几何区域和一致性约束改进遥感开放词汇语义分割，在多个数据集上超越现有方法。

Comments Open-vocabulary, Remote sensing, Geometric prompting, Multimodal large language model

2407.10804 2024-07-16 cs.CL 82%

Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment

Jinhao Jiang, Junyi Li, Wayne Xin Zhao, Yang Song, Tao Zhang, Ji-Rong Wen

专题命中领域大模型：LLM(abstract,comments)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Comments LLM, CPT, knowledge learning, format alignment; work in progress

2511.19759 2026-08-19 cs.CV 版本更新 82%

Vision-Language Enhanced Foundation Model for Semi-Supervised Medical Image Segmentation

增强视觉-语言能力的半监督医学图像分割基础模型

Jiaqi Guo, Mingzhen Li, Hanyu Su, Keigo Healy, Lexiaozi Fan, Neda Tavakoli, Santiago López-Tapia, Daniel Kim, Aggelos K. Katsaggelos

机构 * ECE, Northwestern University（电气工程与计算机科学系，西北大学）； Stats, Northwestern University（统计学系，西北大学）； Radiology, Northwestern University（放射学系，西北大学）

专题命中领域大模型：foundation model(title,abstract)；language model(abstract)

AI总结本文提出VESSA模型，通过增强视觉-语言能力的半监督方法提升医学图像分割精度，实验表明其在有限标注条件下表现优于现有方法。

2608.16131 2026-08-18 cs.CY 新提交 82%

Mitigating AI Risks in Computing Education via LLM-Driven Lecture Video Curation

通过大语言模型驱动的授课视频筛选缓解计算机教育中的人工智能风险

Owen Tang, Alexandra Vassar, Jake Renzella

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)

AI总结本研究测试了LLMs检索授课视频片段回答编程问题的有效性，对比三种模型与人类讲师，发现专有模型表现接近专家，试点部署获学生良好反馈，为安全整合LLMs到计算机课程提供了可行方案。

Comments 7 pages, 3 tables, 1 figure

2607.11621 2026-08-18 cs.AI cs.CL cs.LG 版本更新 82%

Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns

受损多模态语言模型再现失语症患者的图片命名模式

Yong Yang, Xiang Guan, Sophie Arheix-Parras, Saeed Ahmadi, Roger Newman-Norlund, Leonardo Bonilha, Christopher Rorden, Julius Fridriksson, Rutvik H. Desai, Srihari Nelakuditi

专题命中领域大模型：language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结研究未针对临床模拟设计的通用语言模型能否再现失语症患者图片命名错误模式，通过对多模态语言模型进行扰动配置，建立定量框架再现个体失语症错误模式，表明语言模型或可成为中风后失语症患者数字替身。

Comments 15 pages, 8 figures; supplementary materials (18 pages, 6 sections) included

2602.19471 2026-08-11 cs.CV 版本更新 82%

Forgetting-Resistant and Lesion-Aware Source-Free Domain Adaptive Fundus Image Analysis with Vision-Language Model

具有遗忘抵抗性和病变意识的源无关域自适应视网膜图像分析与视觉-语言模型

Zheang Huai, Hui Tang, Hualiang Wang, Xiaomeng Li

机构 * The Hong Kong University of Science（香港科学与技术大学）

专题命中领域大模型：language model(title,abstract)；foundation model(abstract)

AI总结本文提出FRLA方法，通过保留目标模型的自信预测和利用ViL模型的细粒度知识，提升视网膜图像诊断的源无关域自适应性能。

Comments Some experimental results in Section 3 are based on comparisons that may not be entirely fair

2607.26111 2026-07-30 cs.SE 新提交 82%

Validating ETCS Data with the B Mathematical Language: An Industrial Pipeline and a Blueprint for LLM Integration

用B数学语言验证ETCS数据：工业流水线与大语言模型集成蓝图

Thierry Lecomte, Vincent Germain

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)

AI总结本文报告CLEARSY公司ValidAItion项目进展，将ERTMS操作模拟器与CLEARSY数据求解器桥接，用B语言验证ETCS数据，Claude生成规则库，工具链与人工审核裁决，形式化规则为事实来源，大模型为受管控助手。

Comments Submitted and accepted to DisCoRail @ISOLA 2026

2607.20274 2026-07-23 cs.CV cs.AI cs.CL cs.LG 新提交 82%

Self-supervision drives representational convergence in medical foundation models more than clinical supervision

自我监督比临床监督更能推动医学基础模型中的表征趋同

Soroosh Tayebi Arasteh, Sebastian Ziegelmayer, Mahshad Lotfinia, Lisa Adams, Sven Nebelung, Jakob Nikolas Kather, Daniel Truhn

机构 * RWTH Aachen University（亚琛工业大学）； University Hospital RWTH Aachen（亚琛工业大学附属医院）； Technical University of Munich（慕尼黑工业大学）； Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）； Technical University Dresden（德累斯顿工业大学）； University Hospital Dresden（德累斯顿大学附属医院）； University Hospital Heidelberg（海德堡大学附属医院）

专题命中领域大模型：foundation model(title)；pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结研究探讨医学基础模型中表征趋同问题，通过对多个编码器剖析发现自我监督比临床监督更能驱动收敛，虽收敛有限但线性分类器可跨编码器转移，表明医学成像收敛由预训练目标决定，为互操作性设计与验证提供依据。

2607.16083 2026-07-20 cs.SE 新提交 82%

What Does It Take to Research with AI? A Rapid Review of Competencies to Train LLM-Literate Researchers

利用人工智能进行研究需要具备什么？对培养精通大语言模型的研究人员所需能力的快速回顾

Danilo Monteiro Ribeiro, Ronnie de Souza Santos, Rodrigo Siqueira, Breno Andrade, Rafael Batista Duarte, Gilberto Hida, Julia Alencar, Gustavo Pinto

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)

AI总结研究探讨科研中使用大语言模型时研究人员所需能力，通过分析相关文章确定八项能力，指出领域专业知识是关键，培养人员使用大语言模型需综合多方面能力，结果对研究生项目和人工智能素养计划设计有指导意义。

2607.09774 2026-07-14 cs.DL 新提交 82%

Hallucination Detector: A hybrid LLM and Semantic Scholar tool calling for detecting hallucination in scientific literature on AtomGPT.org

幻觉检测器：一种用于在AtomGPT.org上检测科学文献中幻觉的混合大语言模型和语义学者工具调用

Harichandana Neralla, Jaehyung Lee, Aldo H. Romero, Kamal Choudhary

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)

AI总结研究针对大语言模型用于科学写作时出现的虚构参考文献问题，提出结合大语言模型字段提取与语义学者结构化检索的AtomGPT参考文献检查器，经基准测试能可靠标记多数幻觉引用，保障文献引用可信度。

2607.06913 2026-07-09 cs.CY 新提交 82%

Evaluating LLM Robustness Under Domain-Specific Prompt Perturbations in Public Health Applications

在公共卫生应用中评估特定领域提示扰动下的大语言模型稳健性

Chuqing Zhao, Haochen Yang

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)

AI总结研究公共卫生应用中LLMs对特定领域提示扰动的稳健性，提出特定领域稳健性基准，通过错误信息框架和外行重写两种扰动类型评估，揭示两种部署风险，强调需超越干净基线基准进行扰动感知稳健性评估。

2510.13808 2026-07-08 cs.CV 版本更新 82%

VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models

VisCoP：用于视觉语言模型视频域适应的视觉探测

Dominick Reilly, Manish Kumar Govind, Le Xue, Srijan Das

机构 * University of North Carolina at Charlotte（北卡罗来纳州立大学查塔努加分校）； Elorian AI（Elorian人工智能公司）

专题命中领域大模型：language model(title,abstract)；pretraining(abstract)

AI总结研究针对视觉语言模型在新领域性能下降问题，提出参数高效的VisCoP框架，通过可学习视觉探测器增强视觉编码器，在多种适应设置下评估，该框架优于现有策略，能有效适应新领域且保留源域能力。

Comments ECCV 2026

1. 领域大模型 12597 篇

Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Models

ACE-$M^3$: Automatic Capability Evaluator for Multimodal Medical Models

Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling

RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation

Prompt Engineering a Schizophrenia Chatbot: Utilizing a Multi-Agent Approach for Enhanced Compliance with Prompt Instructions

RespLLM: Unifying Audio and Text with Multimodal LLMs for Generalized Respiratory Health Prediction

Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization

Fine-tuning and Prompt Engineering with Cognitive Knowledge Graphs for Scholarly Knowledge Organization

Understanding eGFR Trajectories and Kidney Function Decline via Large Multimodal Models

Aligning (Medical) LLMs for (Counterfactual) Fairness

Bias patterns in the application of LLMs for clinical decision support: A comprehensive study

Zero-Shot Clinical Trial Patient Matching with LLMs

Zero-shot and Few-shot Generation Strategies for Artificial Clinical Records

Retrieval Augmented End-to-End Spoken Dialog Models

Logic-Scaffolding: Personalized Aspect-Instructed Recommendation Explanation Generation using LLMs

Merging Generated and Retrieved Knowledge for Open-Domain QA

S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs

Legal Prompt Engineering for Multilingual Legal Judgement Prediction

RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation

Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment

Vision-Language Enhanced Foundation Model for Semi-Supervised Medical Image Segmentation

Mitigating AI Risks in Computing Education via LLM-Driven Lecture Video Curation

Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns

Forgetting-Resistant and Lesion-Aware Source-Free Domain Adaptive Fundus Image Analysis with Vision-Language Model

Validating ETCS Data with the B Mathematical Language: An Industrial Pipeline and a Blueprint for LLM Integration

Self-supervision drives representational convergence in medical foundation models more than clinical supervision

What Does It Take to Research with AI? A Rapid Review of Competencies to Train LLM-Literate Researchers

Hallucination Detector: A hybrid LLM and Semantic Scholar tool calling for detecting hallucination in scientific literature on AtomGPT.org

Evaluating LLM Robustness Under Domain-Specific Prompt Perturbations in Public Health Applications

VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models