语言大模型 / LLM

AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science

Qiuhai Zeng, Claire Jin, Xinyue Wang, Yuhan Zheng, Qunhua Li

机构 * Pennsylvania State University（宾夕法尼亚州立大学） ； Carnegie Mellon University（卡内基梅隆大学） ； International Monetary Fund（国际货币基金组织） 纠错

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

Comments Accepted to 2025 EMNLP findings

Large Language Model-Derived Priors Can Improve Bayesian Survival Analyses: A Glioblastoma Application

Richard Evans, Max Felland, Susanna Evans, Lindsey Sloan

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

Comments Presented at the 2nd Annual Southeast Wisconsin Data Science (SEAWINDS) Research Symposium, Milwaukee, WI

Who Gets Seen in the Age of AI? Adoption Patterns of Large Language Models in Scholarly Writing and Citation Outcomes

Farhan Kamrul Khan, Hazem Ibrahim, Nouar Aldahoul, Talal Rahwan, Yasir Zaki

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

Comments 11 pages, 5 figures

Cloud-Device Collaborative Agents for Sequential Recommendation

Jing Long, Sirui Huang, Huan Huo, Tong Chen, Hongzhi Yin, Guandong Xu

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

Students' Perceptions to a Large Language Model's Generated Feedback and Scores of Argumentation Essays

Winter Allen, Anand Shanker, N. Sanjay Rebello

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

Comments 7 pages, 4 figures, Physics Education Research Conference 2025

CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning

Mengsong Wu, YaFei Wang, Yidong Ming, Yuqi An, Yuwei Wan, Wenliang Chen, Binbin Lin, Yuqiang Li, Tong Xie, Dongzhan Zhou

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； Soochow University（苏州大学） ； Zhejiang University（浙江大学） ； City University of Hong Kong（香港城市大学） 纠错

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

Comments 15 pages, 6 figures

AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model

Tijmen de Haan, Yuan-Sen Ting, Tirthankar Ghosal, Tuan Dung Nguyen, Alberto Accomazzi, Azton Wells, Nesar Ramachandra, Rui Pan, Zechang Sun

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

Journal ref Sci Rep 15, 13751 (2025)

Academic Literature Recommendation in Large-scale Citation Networks Enhanced by Large Language Models

Kun Liu, Yan Zhang, Rui Pan, Tianchen Gao, Hansheng Wang

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

Explainable Biomedical Claim Verification with Large Language Models

Siting Liang, Daniel Sonntag

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

Leveraging Large Language Models for Cybersecurity: Enhancing SMS Spam Detection with Robust and Context-Aware Text Classification

Mohsen Ahmadi, Matin Khajavi, Abbas Varmaghani, Ali Ala, Kasra Danesh, Danial Javaheri

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

Who Gets Recommended? Investigating Gender, Race, and Country Disparities in Paper Recommendations from Large Language Models

Yifan Tian, Yixin Liu, Yi Bu, Jiqun Liu

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

SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation

Abhishek Divekar, Greg Durrett

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

Comments Published as a main conference paper at EMNLP 2024. Code available at https://github.com/amazon-science/synthesizrr

Health Text Simplification: An Annotated Corpus for Digestive Cancer Education and Novel Strategies for Reinforcement Learning

Md Mushfiqur Rahman, Mohammad Sabik Irbaz, Kai North, Michelle S. Williams, Marcos Zampieri, Kevin Lybarger

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

Comments Published in Journal of Biomedical Informatics, Volume 158, October 2024, 104727

CACTUS: Chemistry Agent Connecting Tool-Usage to Science

Andrew D. McNaughton, Gautham Ramalaxmi, Agustin Kruel, Carter R. Knutson, Rohith A. Varikoti, Neeraj Kumar

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

As an AI Language Model, "Yes I Would Recommend Calling the Police": Norm Inconsistency in LLM Decision-Making

Shomik Jain, D Calacci, Ashia Wilson

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

Comments To appear in the proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES 2024)

Diagnosis Assistant for Liver Cancer Utilizing a Large Language Model with Three Types of Knowledge

Xuzhou Wu, Guangxin Li, Xing Wang, Zeyu Xu, Yingni Wang, Jianming Xian, Xueyu Wang, Gong Li, Kehong Yuan

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

Supporting Business Document Workflows via Collection-Centric Information Foraging with Large Language Models

Raymond Fok, Nedim Lipka, Tong Sun, Alexa Siu

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

Comments 20 pages, 10 figures, 4 tables. Published at CHI 2024

Large Language Models as Data Augmenters for Cold-Start Item Recommendation

Jianling Wang, Haokai Lu, James Caverlee, Ed Chi, Minmin Chen

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

Effectively Fine-tune to Improve Large Multimodal Models for Radiology Report Generation

Yuzhe Lu, Sungmin Hong, Yash Shah, Panpan Xu

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

Comments Accepted to Deep Generative Models for Health Workshop at NeurIPS 2023

Exploring the Value of Pre-trained Language Models for Clinical Named Entity Recognition

Samuel Belkadi, Lifeng Han, Yuping Wu, Goran Nenadic

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

Comments working paper - Large Language Models, Fine-tuning LLMs, Clinical NLP, Medication Mining, AI for Healthcare

SPCXR: Self-supervised Pretraining using Chest X-rays Towards a Domain Specific Foundation Model

Syed Muhammad Anwar, Abhijeet Parida, Sara Atito, Muhammad Awais, Gustavo Nino, Josef Kitler, Marius George Linguraru

专题命中 领域大模型 ：foundation model(title)；pretraining(title)

Can Small Models Reason About Legal Documents? A Comparative Study

小型模型能否对法律文件进行推理？一项比较研究

Snehit Vaddi

机构 * Independent Researcher（独立研究员） 纠错

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

AI总结 本文通过测试九种模型在三个法律基准上的表现，发现3B参数的混合专家模型在法律持有识别上优于GPT-4o-mini，且提示策略影响显著，few-shot提示效果最佳。

Comments 17 pages, 9 models, 5 prompting strategies, 3 legal benchmarks, 405 experiments

GxP-Agent: Process-DAG Topology for Reliable Clinical Trial Programming with LLM Agents

GxP-Agent：基于流程有向无环图拓扑结构的可靠临床试验编程大模型智能体

Jaime Yan

机构 * Harrisburg University of Science and Technology（哈里斯堡科技大学） 纠错

专题命中 领域大模型 ：LLM(title,abstract)；分类 cs.AI

AI总结 该研究提出基于流程DAG拓扑的多智能体系统GxP-Agent，在临床试验编程任务上显著优于现有方法，实现了高结构匹配率，验证了编码领域流程知识为图拓扑的有效性。

Comments Preprint. 9 pages main text, 3 figures, plus references and appendix

MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systems

MUSE：一种用于理解和操控大语言模型驱动的数据科学系统的交互式元智能体

Wei-Hao Chen, Weixi Tong, Yuan Tian, Chenglong Wang, Tianyi Zhang

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

AI总结 本文提出交互式元智能体MUSE，通过重构执行轨迹、支持上下文交互与混合意图操控，提升用户对大语言模型驱动的数据科学系统的理解与控制，经15人被试间研究验证可提高任务效率与用户信心。

Comments To appear in the 39th Annual ACM Symposium on User Interface Software and Technology (UIST '26), November 2-5, 2026, Detroit, MI, USA

Can Generalist Vision Language Models (VLMs) Rival Specialist Medical VLMs? Benchmarking and Strategic Insights

通用视觉语言模型（VLMs）能否在医疗领域超越专门化模型？基准测试与战略洞察

Yuan Zhong, Ruinan Jin, Qi Dou, Xiaoxiao Li

机构 * The Chinese University of Hong Kong（香港中文大学） ； The University of British Columbia（不列颠哥伦比亚大学） ； Vector Institute（向量研究所） 纠错

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

AI总结 研究比较了通用与专门化医疗VLMs的性能，发现高效微调的通用模型在多数任务中表现可比或更优，尤其在处理未见医疗模态时。

Comments version 5

Diffract: Spectral View of LLM Domain Adaptation

Diffract：大语言模型领域自适应的谱视角

Nikita Borodin, Maria Krylova, Artem Zabolotnyi, Dmitry Aspisov, Egor Shikov, Nikita Tyuplyaev, Oleg Travkin, Roman Alferov, Dmitry Vinichenko

专题命中 领域大模型 ：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.LG

AI总结 本研究提出Diffract工具包，通过分析持续预训练的大语言模型的权重矩阵奇异值谱，发现可选择性回退低重要性注意力头以提升领域适配性能，实现高效的领域自适应。

Comments Accepted at ICML 2026. Code: https://github.com/Risk-AI-Research/diffract

Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Models

永不停止说话：针对端到端语音语言模型的拒绝服务攻击

Shuozhe Cheng, Kunlan Xiang, Mingxuan Li, Ji Zhang, Dongxiao Liu, Wenbo Jiang

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

AI总结 本研究针对端到端语音语言模型提出基于扰动的拒绝服务攻击，通过优化声学扰动抑制EOS生成以延长解码，在三类开源模型上验证了其攻击有效性及安全风险。

H2: A Dual Hybrid Semantic Data Lake Architecture for Medical Data Harmonization with Human-In-the-Loop verified, LLM Driven Metadata Annotation System

H2：一种用于医疗数据协调的双混合语义数据湖架构，带有人类在环验证、大语言模型驱动的元数据标注系统

Ioannis N. Tzortzis, Georgia Kapetadimitri, Agapi Davradou, Nefeli Kousta, Nikolaos Bakalos, Ioannis Rallis, Dimitrios Kalogeras, Nikolaos Doulamis, Anastasios Doulamis

机构 * Institute of Communication and Computer Systems (ICCS)（通信与计算机系统研究所（ICCS）） ； University of Macedonia (UOM)（马其顿大学（UOM）） 纠错

专题命中 领域大模型 ：LLM(title,summary_cn)；分类 cs.AI

AI总结 本文提出带人类在环验证、LLM驱动元数据标注系统的双混合语义数据湖架构，解决医疗数据异质性与数据沼泽问题，支撑医疗数据协调及机器学习技术应用。

Comments This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

On the use of foundation models in cognitive science

基础模型在认知科学中的应用

Raj Sanjay Shah, Alex Warstadt, Michael Frank, Sashank Varma

专题命中 领域大模型 ：foundation model(title,abstract)；分类 cs.CL

AI总结 本文针对将基础模型作为认知模型的挑战，提出四阶段推理框架，明确连接假设作用，强调行为对齐需结合理论承诺等才具科学意义。

Do 3D Medical Foundation Models See Through MRI Artifacts? A Controlled Study of Representation Robustness

三维医学基础模型能看穿MRI伪影吗？一项关于表示鲁棒性的对照研究

Julia Anna Mielcarz, Daniel Klaaby, Mostafa Mehdipour Ghazi

机构 * Pioneer Centre for AI, University of Copenhagen（哥本哈根大学先锋人工智能中心） 纠错

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

AI总结 本文对照评估五种三维医学基础模型的表示鲁棒性，发现其鲁棒性与模型及伪影类型相关，部分模型对伪影更敏感，仅靠大规模预训练无法保证伪影不变性，需部署前评估鲁棒性。

Comments Accepted at the ECCV 2026 Workshop on Artificial Intelligence for Medical 3D Vision (AI4M3D)