语言大模型 / LLM

TRAWL: External Knowledge-Enhanced Recommendation with LLM Assistance

Weiqing Luo, Chonggang Song, Lingling Yi, Gong Cheng

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

Comments 8 pages, 3 figures

DALLMi: Domain Adaption for LLM-based Multi-label Classifier

Miruna Beţianu, Abele Mălan, Marco Aldinucci, Robert Birke, Lydia Chen

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

Enhancing Clinical Efficiency through LLM: Discharge Note Generation for Cardiac Patients

HyoJe Jung, Yunha Kim, Heejung Choi, Hyeram Seo, Minkyoung Kim, JiYe Han, Gaeun Kee, Seohyun Park, Soyoung Ko, Byeolhee Kim, Suyeon Kim, Tae Joon Jun, Young-Hak Kim

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

Comments 10 pages, 1 figure, 3 tables, conference

Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases

Jiarui Li, Ye Yuan, Zehua Zhang

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

Comments These authors contributed equally to this work

LLMGuard: Guarding Against Unsafe LLM Behavior

Shubh Goyal, Medha Hira, Shubham Mishra, Sukriti Goyal, Arnav Goel, Niharika Dadu, Kirushikesh DB, Sameep Mehta, Nishtha Madaan

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

Comments accepted in demonstration track of AAAI-24

An LLM Maturity Model for Reliable and Transparent Text-to-Query

Lei Yu, Abir Ray

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

Comments 8 pages, 5 figures

DAEDRA: A language model for predicting outcomes in passive pharmacovigilance reporting

Chris von Csefalvay

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

Evaluating LLM -- Generated Multimodal Diagnosis from Medical Images and Symptom Analysis

Dimitrios P. Panagoulias, Maria Virvou, George A. Tsihrintzis

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

Comments Department of Informatics, University of Piraeus, Greece

Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy

Lin Ni, Sijie Wang, Zeyu Zhang, Xiaoxuan Li, Xianda Zheng, Paul Denny, Jiamou Liu

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

Human-Instruction-Free LLM Self-Alignment with Limited Samples

Hongyi Guo, Yuanshun Yao, Wei Shen, Jiaheng Wei, Xiaoying Zhang, Zhaoran Wang, Yang Liu

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

Data Augmentations for Improved (Large) Language Model Generalization

Amir Feder, Yoav Wald, Claudia Shi, Suchi Saria, David Blei

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

Comments Published at NeurIPS 2023

TigerBot: An Open Multilingual Multitask LLM

Ye Chen, Wei Cai, Liangmin Wu, Xiaowei Li, Zhanxuan Xin, Cong Fu

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

"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters

Yixin Wan, George Pu, Jiao Sun, Aparna Garimella, Kai-Wei Chang, Nanyun Peng

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

Comments Accepted to EMNLP 2023 Findings

Visual In-Context Prompting

Feng Li, Qing Jiang, Hao Zhang, Tianhe Ren, Shilong Liu, Xueyan Zou, Huaizhe Xu, Hongyang Li, Chunyuan Li, Jianwei Yang, Lei Zhang, Jianfeng Gao

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

Comments technical report

ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science

Sai Munikoti, Anurag Acharya, Sridevi Wagle, Sameera Horawalavithana

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

VIP5: Towards Multimodal Foundation Models for Recommendation

Shijie Geng, Juntao Tan, Shuchang Liu, Zuohui Fu, Yongfeng Zhang

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

Comments Accepted by EMNLP 2023

Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, Tom Goldstein

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

Comments 12 pages

Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval

Chunxi Guo, Zhiliang Tian, Jintao Tang, Pancheng Wang, Zhihua Wen, Kang Yang, Ting Wang

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

Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding

Augustin Toma, Patrick R. Lawler, Jimmy Ba, Rahul G. Krishnan, Barry B. Rubin, Bo Wang

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

Comments for model weights, see https://huggingface.co/wanglab/

The Science of Detecting LLM-Generated Texts

Ruixiang Tang, Yu-Neng Chuang, Xia Hu

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

MedAide: Information Fusion and Anatomy of Medical Intents via LLM-based Agent Collaboration

Dingkang Yang, Jinjie Wei, Mingcheng Li, Jiyao Liu, Lihao Liu, Ming Hu, Junjun He, Yakun Ju, Wei Zhou, Yang Liu, Lihua Zhang

机构 * 1 College of Intelligent Robotics ； Advanced Manufacturing, Fudan University \, 2 Multimodal Foundation Research Team, CIT Lab [1mm] 3 Shanghai Artificial Intelligence Laboratory \, 4 Institute of Science ； Technology for Brain-Inspired Intelligence, Fudan University [1mm] 5 School of Computing ； Mathematical Sciences, University of Leicester \, 6 Cardiff University [1mm] 7 Department of Computer Science, The University of Toronto \, 8 Institute of Metaverse \& Intelligent Medicine [1mm] 9 Jilin Provincial Key Laboratory of Intelligence Science ； Engineering [1mm] 10 Engineering Research Center of AI 纠错

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

Comments LLM-based Multi-Agent Collaboration for Medical Applications

Empowering Compact LLMs with Fusion of Layer-wise Exits for Recommendation

融合分层出口的紧凑型大语言模型推荐系统

Xurong Liang, Tong Chen, Quoc Viet Hung Nguyen, Jianxin Li, Xiangliang Zhang, Hongzhi Yin

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

AI总结 本文提出FLEXRec框架，通过在紧凑型LLM的Transformer层插入预测头并自适应融合，结合AC-Router与目标k铰链损失，在三个数据集上以Qwen 3 1.7B和Llama 3.2 3B实现紧凑型主干方法中最优准确率且效率高。

Comments Accepted by ICDM'26

Consensus-gated Multi-Agent Neural Architecture Search for Seismic Fault Segmentation

面向地震断层分割的共识门控多智能体神经架构搜索

Shehram Baig, Ahmad Mustafa

机构 * Information Technology University (ITU)（信息技术大学（ITU）） ； King Fahd University of Petroleum and Minerals（法赫德国王石油与矿业大学） 纠错

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

AI总结 提出共识门控多智能体NAS系统，利用三个LLM达成共识搜索架构，发现参数42.5万的\textit{ours}模型，在Thebe断层数据集上性能优于多个基准模型，成本低、效率高。

How LLMs Respond to Escalating Delusions: Four Longitudinal Trajectories of Model Behavior

大语言模型（LLM）对日益严重的妄想的反应：模型行为的四种纵向轨迹

Anna Sterna, Kacper Dudzic, Karolina Drożdż, Hubert Plisiecki, Marcin Rządeczka, Marcin Moskalewicz

专题命中 领域大模型 ：LLM(title_cn,summary_cn)

AI总结 本研究通过30天的纵向实验，评估15种主流LLM对模拟精神症状进展的反应，识别出四种不同行为轨迹，提出需从识别时机、稳定性和干预准确性维度纵向评估LLM加剧AI精神病的潜力。

Generalizable Operating Room Expert with Multimodal Enhancement

具备多模态增强能力的可泛化手术室专家

Peiqi He, Zhenhao Zhang, Yixiang Zhang, Jiaxin Liu, Xiongjun Zhao, Shaoliang Peng

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

AI总结 针对手术室空间建模的局限，提出仅用RGB图像推理的多模态大语言模型OR-Expert，通过内部推导空间线索实现三维推理，在手术室基准上达SOTA且泛化性良好。

Comments Accepted by ACM Multimedia 2026

A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench

针对特定语料库的临床检索增强生成（RAG）系统在HealthBench上的表现与较新的前沿大语言模型相当或更优

Praveen Reddy, Charuta Mandke, Suvrankar Datta, Sarah Khan, Siddharth Reddy Anthireddy, Shitij Arora, Vishal Singh

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

AI总结 本文评估专为中低收入环境构建的临床RAG系统VITA，其在HealthBench基准测试中与前沿LLM表现相当或更优，语料库特异性可提升模型落地性但会降低沟通流畅度。

Comments 2 tables

Harnessing LLMs for Document-Guided Fuzzing of Python Libraries

利用大语言模型（LLM）实现Python库的文档引导模糊测试

Bin Duan, Tarek Mahmud, Meiru Che, Yan Yan, Naipeng Dong, Dan Dongseong Kim, Guowei Yang

专题命中 领域大模型 ：LLM(title_cn,summary_cn)

AI总结 本文提出VistaFuzz，一种基于本地开源LLM的文档引导模糊测试技术，用于测试Python库API，在12个库的7718个API上发现74个问题，其中43个已确认、29个已修复。

Automated Synthesis of Deterministic Cross-Domain Interfaces

确定性跨域接口的自动合成

Konstantinos Christodoulopoulos, Antonis Selentis-Boulntadakis

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

AI总结 该研究提出框架，利用LLM实现智能体与处理程序模块，自动合成跨域确定性网络的静态、动态契约，经实验验证其动态契约性能优于静态配置，且分工模式可保障模型可靠性。

Calibrating Trustworthiness: Co-Designing Metrics and Visualizations for Evaluating LLMs in Education

校准可信度：为教育领域评估大型语言模型（LLM）协同设计指标与可视化方案

Adam Coscia, Sujata Duwal, Langdon Holmes, Scott Crossley, Alex Endert

专题命中 领域大模型 ：LLM(title_cn,summary_cn)

AI总结 本研究针对教育领域LLM响应的教学适配性评估缺口，通过与学习工程师协同设计可信度指标与可视化工具，提升了评估信度，为相关工具提出设计准则。

Comments Under review. 48 pages, 22 figures, 2 tables

TrainShield: Targeted Awareness for Cybersecurity Training

TrainShield：面向网络安全培训的目标感知机制

Giovanni Pizzenti, Alberto Verna, Nikhil Jha, Giuseppe Tipaldo, Stefano Traverso, Marco Mellia

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

AI总结 本研究提出嵌入用户工作流的场景化网络安全培训范式TrainShield，结合实时风险检测与LLM生成内容，初步验证其可提升风险意识，为行为导向网络安全教育提供新方向。

Comments Paper accepted for publication at ACM Hypertext 2026