语言大模型 / LLM

2504.15800 2025-09-04 cs.IR 67%

FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation

Chanyeol Choi, Jihoon Kwon, Jaeseon Ha, Hojun Choi, Chaewoon Kim, Yongjae Lee, Jy-yong Sohn, Alejandro Lopez-Lira

专题命中评测与基准：large language model(abstract)；language model(abstract)

Comments 10 pages, 3 figures, ICLR 2025 Workshop Advances in Financial AI

2505.17137 2025-09-04 cs.CL cs.AI 62%

Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands

Kristin Qi, Youxiang Zhu, Caroline Summerour, John A. Batsis, Xiaohui Liang

机构 * Computer Science, University of Massachusetts, Boston, MA, USA（计算机科学，马萨诸塞大学，波士顿，马萨诸塞州，美国）； School of Medicine, University of North Carolina, Chapel Hill, NC, USA（医学院，北卡罗来纳大学，夏洛特，北卡罗来纳州，美国）

专题命中评测与基准：LLM(abstract)；分类 cs.CL、cs.AI

Comments IEEE Global Communications Conference (GlobeCom) 2025

2505.05225 2025-09-04 cs.CL 57%

QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation

Mengze Hong, Wailing Ng, Chen Jason Zhang, Di Jiang

机构 * Hong Kong Polytechnic University（香港理工大学）； AI Group, WeBank Co., Ltd（WeBank公司人工智能部）

专题命中评测与基准：LLM(abstract)；分类 cs.CL

Comments Accepted by EMNLP 2025 Main Conference. Homepage: https://github.com/mengze-hong/QualBench

2509.03037 2025-09-04 cs.CR cs.ET cs.SE 50%

TraceLLM: Security Diagnosis Through Traces and Smart Contracts in Ethereum

Shuzheng Wang, Yue Huang, Zhuoer Xu, Yuming Huang, Jing Tang

专题命中评测与基准：LLM(abstract)

2509.01275 2025-09-04 cs.CV 50%

Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation

Jiahao Li, Yang Lu, Yachao Zhang, Fangyong Wang, Yuan Xie, Yanyun Qu

专题命中评测与基准：language model(abstract)

Comments Accepted by ACMMM2025

2508.09600 2025-09-04 cs.SD 50%

OSUM-EChat: Enhancing End-to-End Empathetic Spoken Chatbot via Understanding-Driven Spoken Dialogue

Xuelong Geng, Qijie Shao, Hongfei Xue, Shuiyuan Wang, Hanke Xie, Zhao Guo, Yi Zhao, Guojian Li, Wenjie Tian, Chengyou Wang, Zhixian Zhao, Kangxiang Xia, Ziyu Zhang, Zhennan Lin, Tianlun Zuo, Mingchen Shao, Yuang Cao, Guobin Ma, Longhao Li, Yuhang Dai, Dehui Gao, Dake Guo, Lei Xie

专题命中评测与基准：language model(abstract)

2509.03058 2025-09-04 cs.CR 89%

EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint

Zhenhua Xu, Meng Han, Wenpeng Xing

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments Accepted by EMNLP2025 Main

2406.15486 2025-09-04 cs.CL cs.AI cs.LG 87%

SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention

Qianchao Zhu, Jiangfei Duan, Chang Chen, Siran Liu, Guanyu Feng, Xin Lv, Xiao Chuanfu, Dahua Lin, Chao Yang

专题命中效率与部署：LLM(title)；large language model(abstract)；language model(abstract)；pretraining(abstract)

2509.03462 2025-09-04 cs.AI cs.CV cs.RO 85%

sam-llm: interpretable lane change trajectoryprediction via parametric finetuning

Zhuo Cao, Yunxiao Shi, Min Xu

机构 * University of Queensland, School of Civil Engineering（昆士兰大学土木工程学院）； University of Technology Sydney, Faculty of Engineering（悉尼科技大学工程学院）

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 5 pages

2508.10059 2025-09-04 cs.SE 85%

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement

Yueke Zhang, Yifan Zhang, Kevin Leach, Yu Huang

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments 6 Pages

2507.06463 2025-09-04 cs.SE 85%

Evaluating Efficiency and Novelty of LLM-Generated Code for Graph Analysis

Atieh Barati Nia, Mohammad Dindoost, David A. Bader

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)

Comments 7 pages, v2: minor revision to match final paper published in the The 29th Annual IEEE High Performance Extreme Computing Conference (HPEC), Virtual, September 15-19, 2025. Outstanding Student Paper Award

2410.16033 2025-09-04 cs.CL cs.AI cs.LG 83%

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling

Jiahao Qiu, Yifu Lu, Yifan Zeng, Jiacheng Guo, Jiayi Geng, Chenhao Zhu, Xinzhe Juan, Ling Yang, Huazheng Wang, Kaixuan Huang, Yue Wu, Mengdi Wang

专题命中效率与部署：large language model(abstract)；language model(abstract)；RLHF(abstract)；preference optimization(abstract)

2509.03018 2025-09-04 cs.DC cs.LG 79%

Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training

Yangtao Deng, Lei Zhang, Qinlong Wang, Xiaoyun Zhi, Xinlei Zhang, Zhuo Jiang, Haohan Xu, Lei Wang, Zuquan Song, Gaohong Liu, Yang Bai, Shuguang Wang, Wencong Xiao, Jianxi Ye, Minlan Yu, Hong Xu

机构 * The Chinese University of Hong Kong（香港中文大学）； ByteDance（字节跳动）； ByteDance Seed（字节跳动种子）； Harvard University（哈佛大学）

专题命中效率与部署：LLM(title,abstract)；分类 cs.LG

2407.00079 2025-09-04 cs.DC cs.AI cs.AR 79%

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Ruoyu Qin, Zheming Li, Weiran He, Mingxing Zhang, Yongwei Wu, Weimin Zheng, Xinran Xu

机构 * Moonshot AI ； Tsinghua University（清华大学）

专题命中效率与部署：LLM(title,abstract)；分类 cs.AI

Comments 23 pages, 13 figures

2506.19992 2025-09-04 cs.LG cs.AI 79%

HERCULES: Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization

Gabor Petnehazi, Bernadett Aradi

机构 * University of Debrecen（德布勒恩大学）

专题命中效率与部署：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

2509.03047 2025-09-04 cs.DC cs.AI 77%

FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs

Haijun Zhang, Jinxiang Wang, Zhenhua Yu, Yanyong Zhang, Xuejie Ji, Kaining Mao, Jun Zhang, Yaqing Zhang, Ting Wu, Fei Jie, Xiemin Huang, Zhifang Cai, Junhua Cheng, Shuwei Wang, Wei Li, Xiaoming Bao, Hua Xu, Shixiong Zhao, Jun Li, Hongwei Sun, Ziyang Zhang, Yi Xiong, Chunsheng Li

机构 * iFLYTEK AI Engineering Institute（iFLYTEK人工智能工程研究院）； University of Science and Technology of China（中国科学技术大学）； Huawei Technologies Co., Ltd（华为技术有限公司）

专题命中效率与部署：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2507.20301 2025-09-04 cs.CL 77%

Advancing Dialectal Arabic to Modern Standard Arabic Machine Translation

Abdullah Alabdullah, Lifeng Han, Chenghua Lin

机构 * University of Manchester（曼彻斯特大学）； School of Informatics, University of Edinburgh（爱丁堡大学信息学院）； Leiden University（莱顿大学）； LIACS ； LUMC

专题命中效率与部署：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL

2503.00634 2025-09-04 cs.LG cs.AI 73%

Efficiently Editing Mixture-of-Experts Models with Compressed Experts

Yifei He, Yang Liu, Chen Liang, Hany Hassan Awadalla

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Microsoft（微软公司）

专题命中效率与部署：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments EMNLP 2025 Findings

2509.00096 2025-09-04 cs.LG cs.CL 73%

Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs

Yao Fu, Runchao Li, Xianxuan Long, Haotian Yu, Xiaotian Han, Yu Yin, Pan Li

机构 * Case Western Reserve University（凯斯西储大学）； Hangzhou Dianzi University（杭州电子科技大学）

专题命中效率与部署：LLM(abstract)；prompting(abstract)；分类 cs.CL、cs.LG

Comments Accepted to EMNLP2025 findings (poster)

2509.03136 2025-09-04 cs.DB cs.AI 70%

Adaptive KV-Cache Compression without Manually Setting Budget

Chenxia Tang, Jianchun Liu, Hongli Xu, Liusheng Huang

专题命中效率与部署：large language model(abstract)；language model(abstract)；分类 cs.AI

2509.03380 2025-09-04 cs.AI cs.CL 62%

Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems

Peter J. Bentley, Soo Ling Lim, Fuyuki Ishikawa

专题命中效率与部署：LLM(abstract)；分类 cs.CL、cs.AI

Comments 9 pages

Journal ref 7th International Workshop on Agent-Based Modelling of Human Behaviour (ABMHuB'25), ALife 2025

2509.03173 2025-09-04 eess.IV cs.CV cs.LG 57%

Deep Self-knowledge Distillation: A hierarchical supervised learning for coronary artery segmentation

Mingfeng Lin

机构 * Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学深圳学院）； Xiamen University, Xiamen, China（厦门大学）

专题命中效率与部署：prompting(abstract)；分类 cs.LG

2509.02753 2025-09-04 cs.LG 57%

LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference

Krishna Teja Chitty-Venkata, Sandeep Madireddy, Murali Emani, Venkatram Vishwanath

机构 * Argonne National Laboratory（阿贡国家实验室）

专题命中效率与部署：post-training(abstract)；分类 cs.LG

Comments Preprint

2509.03002 2025-09-04 cs.CV 50%

SOPSeg: Prompt-based Small Object Instance Segmentation in Remote Sensing Imagery

Chenhao Wang, Yingrui Ji, Yu Meng, Yunjian Zhang, Yao Zhu

专题命中效率与部署：prompting(abstract)

2507.02654 2025-09-04 cs.AR 50%

Breaking the HBM Bit Cost Barrier: Domain-Specific ECC for AI Inference Infrastructure

Rui Xie, Asad Ul Haq, Yunhua Fang, Linsen Ma, Sanchari Sen, Swagath Venkataramani, Liu Liu, Tong Zhang

专题命中效率与部署：LLM(abstract)

2509.03036 2025-09-04 cs.LG cs.AI cs.IR cs.SC 90%

Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models

Bilge Taskin, Wenxiong Xie, Teddy Lazebnik

机构 * Department of Computing Jonkoping University（乔恩考普大学计算机系）； Department of Information Science University of Haifa（海法大学信息科学系）

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

2509.02876 2025-09-04 cs.RO 89%

Generalizable Skill Learning for Construction Robots with Crowdsourced Natural Language Instructions, Composable Skills Standardization, and Large Language Model

Hongrui Yu, Vineet R. Kamat, Carol C. Menassa

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

Comments Under review for ASCE OPEN: Multidisciplinary Journal of Civil Engineering

2509.02710 2025-09-04 physics.med-ph cs.CV cs.LG 83%

Toward a robust lesion detection model in breast DCE-MRI: adapting foundation models to high-risk women

Gabriel A. B. do Nascimento, Vincent Dong, Guilherme J. Cavalcante, Alex Nguyen, Thaís G. do Rêgo, Yuri Malheiros, Telmo M. Silva Filho, Carla R. Zeballos Torrez, James C. Gee, Anne Marie McCarthy, Andrew D. A. Maidment, Bruno Barufaldi

机构 * University of Pennsylvania（宾夕法尼亚大学）； Federal University of Paraíba（帕拉分校联邦大学）； University of Bristol（布里斯托大学）

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

2509.03421 2025-09-04 eess.IV cs.CV 78%

Generalist versus Specialist Vision Foundation Models for Ocular Disease and Oculomics

Yukun Zhou, Paul Nderitu, Jocelyn Hui Lin Goh, Justin Engelmann, Siegfried K. Wagner, Anran Ran, Hongyang Jiang, Lie Ju, Ke Zou, Sahana Srinivasan, Hyunmin Kim, Takahiro Ninomiya, Zheyuan Wang, Gabriel Dawei Yang, Eden Ruffell, Dominic Williamson, Rui Santos, Gabor Mark Somfai, Carol Y. Cheung, Tien Yin Wong, Daniel C. Alexander, Yih Chung Tham, Pearse A. Keane

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

Comments 39 pages, 8 Figures

2509.02605 2025-09-04 cs.MA cs.AI cs.CY 77%

Synthetic Founders: AI-Generated Social Simulations for Startup Validation Research in Computational Social Science

Jorn K. Teutloff

机构 * Marymount University（玛丽mount大学）

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

Comments Manuscript submitted to the Journal of Artificial Societies and Social Simulation (JASSS). 21 pages, 1 table

1. 评测与基准 27 篇

FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation

Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands

QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation

TraceLLM: Security Diagnosis Through Traces and Smart Contracts in Ethereum

Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation

OSUM-EChat: Enhancing End-to-End Empathetic Spoken Chatbot via Understanding-Driven Spoken Dialogue

2. 效率与部署 19 篇

EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint

SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention

sam-llm: interpretable lane change trajectoryprediction via parametric finetuning

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement

Evaluating Efficiency and Novelty of LLM-Generated Code for Graph Analysis

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling

Mycroft: Tracing Dependencies in Collective Communication Towards Reliable LLM Training

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

HERCULES: Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization

FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs

Advancing Dialectal Arabic to Modern Standard Arabic Machine Translation

Efficiently Editing Mixture-of-Experts Models with Compressed Experts

Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs

Adaptive KV-Cache Compression without Manually Setting Budget

Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems

Deep Self-knowledge Distillation: A hierarchical supervised learning for coronary artery segmentation

LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference

SOPSeg: Prompt-based Small Object Instance Segmentation in Remote Sensing Imagery

Breaking the HBM Bit Cost Barrier: Domain-Specific ECC for AI Inference Infrastructure

3. 领域大模型 10 篇

Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models

Generalizable Skill Learning for Construction Robots with Crowdsourced Natural Language Instructions, Composable Skills Standardization, and Large Language Model

Toward a robust lesion detection model in breast DCE-MRI: adapting foundation models to high-risk women

Generalist versus Specialist Vision Foundation Models for Ocular Disease and Oculomics

Synthetic Founders: AI-Generated Social Simulations for Startup Validation Research in Computational Social Science