语言大模型 / LLM

Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL

Wei Yao, Wenkai Yang, Ziqiao Wang, Yankai Lin, Yong Liu

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments Accepted by ACL 2025 (Findings)

A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment

Edward Y. Chang

机构 * stan（斯坦福大学） ； Computer Science, Stanford University（斯坦福大学计算机科学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 20 pages, 7 tables, 6 figures. arXiv admin note: substantial text overlap with arXiv:2405.07076

MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations

The Viet Bui, Tien Mai, Hong Thanh Nguyen

机构 * Singapore Management University（新加坡国立管理大学） ； University of Oregon（俄勒冈大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Fundamental Limitations on Subquadratic Alternatives to Transformers

Josh Alman, Hantao Yu

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

AI-generated Text Detection: A Multifaceted Approach to Binary and Multiclass Classification

Harika Abburi, Sanmitra Bhattacharya, Edward Bowen, Nirmala Pudota

机构 * Deloitte & Touche Assurance and Enterprise Risk Services India Private Limited（德勤印度审计与企业风险管理服务有限公司） ； Deloitte & Touche LLP（德勤联合事务所） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithms

Jacob Trauger, Ambuj Tewari

机构 * Department of Statistics University of Michigan（统计学系 密歇根大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments 23 pages

Low-Resource Language Processing: An OCR-Driven Summarization and Translation Pipeline

Hrishit Madhavi, Jacob Cherian, Yuvraj Khamkar, Dhananjay Bhagat

机构 * Department of Computer Engineering and Technology（计算机工程与技术系） ； MIT World Peace University（MIT世界和平大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 8 pages, 7 figures, direct arXiv submission

ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution

Xu Huang, Weiwen Liu, Xingshan Zeng, Yuefeng Huang, Xinlong Hao, Yuxian Wang, Yirong Zeng, Chuhan Wu, Yasheng Wang, Ruiming Tang, Defu Lian

机构 * University of Science and Technology of China（中国科学技术大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Huawei Technologies Co., Ltd（华为技术有限公司） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

QiMeng-TensorOp: Automatically Generating High-Performance Tensor Operators with Hardware Primitives

Xuzhi Zhang, Shaohui Peng, Qirui Zhou, Yuanbo Wen, Qi Guo, Ruizhi Chen, Xinguo Zhu, Weiqiang Xiong, Haixin Chen, Congying Ma, Ke Gao, Chen Zhao, Yanjun Wu, Yunji Chen, Ling Li

机构 * Institute of Software Chinese Academy of Sciences（中国科学院软件研究所） ； Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） ； Peking University（北京大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments 10 pages, 5 figures

E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation

Yun Jiang, Zilong Xie, Wei Zhang, Yun Fang, Shuai Pan

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 13 pages, 3 figures, 5 tables

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate

Zhiqi Bu, Xiaomeng Jin, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Mingyi Hong

机构 * Amazon AGI（亚马逊人工智能研究院） ； UIUC（伊利诺伊大学香槟分校） ； Amazon AGI & UCLA（亚马逊人工智能研究院与加州大学洛杉矶分校） ； Amazon AGI & LIONS EPFL（亚马逊人工智能研究院与洛桑联邦理工学院） ； Amazon AGI & University of Minnesota（亚马逊人工智能研究院与明尼苏达大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted to NAACL 2025 main conference

Incentivizing Inclusive Contributions in Model Sharing Markets

Enpei Zhang, Jingyi Chai, Rui Ye, Yanfeng Wang, Siheng Chen

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers

Quentin Guimard, Moreno D'Incà, Massimiliano Mancini, Elisa Ricci

机构 * University of Trento（特伦托大学） ； Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会） 纠错

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments CVPR 2025. Code: https://github.com/mardgui/C2B

Confidence Estimation for Error Detection in Text-to-SQL Systems

Oleg Somov, Elena Tutubalina

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments 15 pages, 11 figures, to be published in AAAI 2025 Proceedings

A Baseline for Self-state Identification and Classification in Mental Health Data: CLPsych 2025 Task

Laerdon Kim

机构 * Cornell University（康奈尔大学） 纠错

专题命中 其他LLM ：LLM(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted to CLPsych Workshop, NAACL 2025

Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models

Chen Wang, Fei Xia, Wenhao Yu, Tingnan Zhang, Ruohan Zhang, C. Karen Liu, Li Fei-Fei, Jie Tan, Jacky Liang

机构 * Google DeepMind（谷歌DeepMind） ； Stanford University（斯坦福大学） 纠错

专题命中 其他LLM ：language model(abstract)；prompting(abstract)；分类 cs.AI、cs.LG

Comments ICRA 2025

SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems

Patrick Emami, Zhaonan Li, Saumya Sinha, Truc Nguyen

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted at ICLR 2025. 23 pages. Updated with final camera ready version

Language-Dependent Political Bias in AI: A Study of ChatGPT and Gemini

Dogus Yuksel, Mehmet Cem Catalbas, Bora Oc

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 26 pages, 10 figures

A Geometric-Aware Perspective and Beyond: Hybrid Quantum-Classical Machine Learning Methods

Azadeh Alavia, Hossein Akhoundib, Fatemeh Kouchmeshkib, Mojtaba Mahmoodianc, Sanduni Jayasinghec, Yongli Rena, Abdolrahman Alavi

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments 19 pages, 3 figures

DiVA-DocRE: A Discriminative and Voice-Aware Paradigm for Document-Level Relation Extraction

Yiheng Wu, Roman Yangarber, Xian Mao

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments After internal discussions among the co-authors, we have decided to withdraw the manuscript due to a change in research direction and a lack of unanimous agreement to proceed with publication at this time

Emojis Decoded: Leveraging ChatGPT for Enhanced Understanding in Social Media Communications

Yuhang Zhou, Paiheng Xu, Xiyao Wang, Xuan Lu, Ge Gao, Wei Ai

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by the 19th International AAAI Conference on Web and Social Media (ICWSM 2025)

Redefining technology for indigenous languages

Silvia Fernandez-Sabido, Laura Peniche-Sabido

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments in Spanish language

Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph

Lingxiao Guan, Yuanhao Huang, Jie Liu

专题命中 其他LLM ：language model(abstract)；small language model(abstract)；分类 cs.CL、cs.AI

Olympus: A Universal Task Router for Computer Vision Tasks

Yuanze Lin, Yunsheng Li, Dongdong Chen, Weijian Xu, Ronald Clark, Philip H. S. Torr

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to CVPR 2025, Project webpage: http://yuanze-lin.me/Olympus_page/

Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering

Federico Cocchi, Nicholas Moratelli, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments CVPR 2025

Automated Explanation of Machine Learning Models of Footballing Actions in Words

Pegah Rahimian, Jernej Flisar, David Sumpter

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

PICLe: Pseudo-Annotations for In-Context Learning in Low-Resource Named Entity Detection

Sepideh Mamooler, Syrielle Montariol, Alexander Mathis, Antoine Bosselut

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments In Proceedings of NAACL2025

Bias-Aware Agent: Enhancing Fairness in AI-Driven Knowledge Retrieval

Karanbir Singh, William Ngu

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Sociotechnical Effects of Machine Translation

Joss Moorkens, Andy Way, Séamus Lankford

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization

Zhecheng Li, Yiwei Wang, Bryan Hooi, Yujun Cai, Naifan Cheung, Nanyun Peng, Kai-wei Chang

专题命中 其他LLM ：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI