语言大模型 / LLM

Tensorized Clustered LoRA Merging for Multi-Task Interference

Zhan Su, Fengran Mo, Guojun Liang, Jinghan Zhang, Bingbing Wen, Prayag Tiwari, Jian-Yun Nie

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

ZenFlow: Enabling Stall-Free Offloading Training via Asynchronous Updates

Tingfeng Lan, Yusen Wu, Bin Ma, Zhaoyuan Su, Rui Yang, Tekin Bicer, Masahiro Tanaka, Olatunji Ruwase, Dong Li, Yue Cheng

机构 * University of Virginia（弗吉尼亚大学） ； University of California, Merced（加州大学梅尔塞德斯分校） ； Argonne National Laboratory（阿贡国家实验室） ； Snowflake AI Research（Snowflake人工智能研究） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.LG

Comments 13 pages, 16 figures

Enhancing the Preference Extractor in Multi-turn Dialogues: From Annotating Disasters to Accurate Preference Extraction

Cheng Wang, ziru Liu, Pengcheng Tang, Mingyu Zhang, Quanyu Dai, Yue Zhu

机构 * Huawei Technologies Co., Ltd.（华为技术有限公司） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL

Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report

Sajana Weerawardhena, Paul Kassianik, Blaine Nelson, Baturay Saglam, Anu Vellore, Aman Priyanshu, Supriti Vijay, Massimo Aufiero, Arthur Goldblatt, Fraser Burch, Ed Li, Jianliang He, Dhruv Kedia, Kojin Oshiba, Zhouran Yang, Yaron Singer, Amin Karbasi

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 34 pages - Technical Report

CollabLLM: From Passive Responders to Active Collaborators

Shirley Wu, Michel Galley, Baolin Peng, Hao Cheng, Gavin Li, Yao Dou, Weixin Cai, James Zou, Jure Leskovec, Jianfeng Gao

机构 * stanford（斯坦福大学） ； microsoft（微软公司） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Outstanding Paper Award at ICML 2025

Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security

Muzhi Dai, Shixuan Liu, Zhiyuan Zhao, Junyu Gao, Hao Sun, Xuelong Li

机构 * Institute of Artificial Intelligence (TeleAI), China Telecom, China（人工智能研究院（TeleAI），中国电信，中国） ； Northwestern Polytechnical University（西北工业大学） ； China Telecom, China（中国电信，中国） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；SFT(abstract)；分类 cs.AI

Comments 10 pages, 4 figures

Libra: Large Chinese-based Safeguard for AI Content

Ziyang Chen, Huimu Yu, Xing Wu, Dongqin Liu, Songlin Hu

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；pretraining(abstract)；分类 cs.AI

SDD: Self-Degraded Defense against Malicious Fine-tuning

Zixuan Chen, Weikai Lu, Xin Lin, Ziqian Zeng

机构 * Zixuan Chen（陈子轩） ； Weikai Lu（卢伟凯） ； Xin Lin（林鑫） ； Ziqian Zeng（曾子谦） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted by ACL2025

The Impact of LoRA Adapters on LLMs for Clinical Text Classification Under Computational and Data Constraints

Thanh-Dung Le, Ti Ti Nguyen, Vu Nguyen Ha, Symeon Chatzinotas, Philippe Jouvet, Rita Noumeir

机构 * Biomedical Information Processing Lab, \' E cole de Technologie Sup\' e rieure, Montr\' e al, Qu\' e bec, Canada ； The Interdisciplinary Centre for Security, Reliability ； Trust (SnT), University of Luxembourg, Luxembourg ； CHU Sainte-Justine Research Center, CHU Sainte-Justine Hospital, University of Montreal, Montr\' e al, Qu\' e bec, Canada 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted for publication in the IEEE Access

P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts

Yuhao Dan, Jie Zhou, Qin Chen, Junfeng Tian, Liang He

机构 * School of Computer Science and Technology, East China Normal University（东华大学计算机科学与技术学院） ； Shanghai Institute of AI for Education, East China Normal University（东华大学人工智能教育研究所） ； Xiaohongshu Inc.（小红书公司） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs

Zixiao Wang, Duzhen Zhang, Ishita Agrawal, Shen Gao, Le Song, Xiuying Chen

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） ； Shandong University（山东省大学） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted by ACL 2025 Findings

CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards

Cheng Liu, Yifei Lu, Fanghua Ye, Jian Li, Xingyu Chen, Feiliang Ren, Zhaopeng Tu, Xiaolong Li

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；language agent(abstract)；分类 cs.CL

Error-Aware Curriculum Learning for Biomedical Relation Classification

Sinchani Chakraborty, Sudeshna Sarkar, Pawan Goyal

机构 * Department of Computer Science and Engineering（计算机科学与工程系） ； Indian Institute of Technology Kharagpur（印度理工学院Khargapur） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；instruction tuning(abstract)；分类 cs.CL

Comments 16 pages, 2 figures

Sparse Rewards Can Self-Train Dialogue Agents

Barrett Martin Lattimer, Varun Gangal, Ryan McDonald, Yi Yang

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to ACL 2025 (Findings)

Visual Position Prompt for MLLM based Visual Grounding

Wei Tang, Yanpeng Sun, Qinying Gu, Zechao Li

机构 * School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；SFT(abstract)；分类 cs.AI

Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix

Ming Wen, Jiaqi Zhu, Yuedong Xu, Yipeng Zhou, Dingding Han

机构 * Department of Electronic Engineering（电子工程系） ； Fudan University（复旦大学） ； School of Computing（计算学院） ； Macquarie University（麦觉瑞大学） ； Department of Communication Science and Engineering（通信科学与工程系） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 23 pages, NeurIPS 2025 under review

OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique

Wasi Uddin Ahmad, Somshubra Majumdar, Aleksander Ficek, Sean Narenthiran, Mehrzad Samadi, Jocelyn Huang, Siddhartha Jain, Vahid Noroozi, Boris Ginsburg

机构 * NVIDIA Santa Clara, CA 95051, USA（英伟达圣克拉拉分校） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments work in progress

Emergent Natural Language with Communication Games for Improving Image Captioning Capabilities without Additional Data

Parag Dutta, Ambedkar Dukkipati

机构 * Department of Computer Science and Automation（计算机科学与自动化系） ； Indian Institute of Science（印度科学院） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Few-shot text-based emotion detection

Teodor-George Marchitan, Claudiu Creanga, Liviu P. Dinu

机构 * University of Bucharest（巴尔干大学） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL

DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs

Mohammad Akyash, Kimia Azar, Hadi Kamali

机构 * Department of Electrical and Computer Engineering (ECE), University of Central Florida（电子与计算机工程系，中央佛罗里达大学） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Accepted to the International Conference on Computer-Aided Design (ICCAD 2025)

Agent-as-Tool: A Study on the Hierarchical Decision Making with Reinforcement Learning

Yanfei Zhang

机构 * Independent Researcher（独立研究者） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 12 pages

Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles

Kuang Wang, Xianfei Li, Shenghao Yang, Li Zhou, Feng Jiang, Haizhou Li

机构 * SRIBD, School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong（香港中文大学（深圳）数据科学学院） ； Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology（深圳先进技术大学人工智能研究院） ； Department of ECE, National University of Singapore（新加坡国立大学电子工程系） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 9 pages. Accepted to ACL 2025. Camera-ready version

Bridging Offline and Online Reinforcement Learning for LLMs

Jack Lanchantin, Angelica Chen, Janice Lan, Xian Li, Swarnadeep Saha, Tianlu Wang, Jing Xu, Ping Yu, Weizhe Yuan, Jason E Weston, Sainbayar Sukhbaatar, Ilia Kulikov

机构 * FAIR at Meta（Meta 的 FAIR 部门） ； NYU（纽约大学） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；preference optimization(abstract)；分类 cs.CL

MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing

Asif Rahman, Veljko Cvetkovic, Kathleen Reece, Aidan Walters, Yasir Hassan, Aneesh Tummeti, Bryan Torres, Denise Cooney, Margaret Ellis, Dimitrios S. Nikolopoulos

机构 * Department of Computer Science, Virginia Tech（计算机科学系，弗吉尼亚理工大学） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 9 pages, 4 figures, 2 tables

LGAI-EMBEDDING-Preview Technical Report

Jooyoung Choi, Hyun Kim, Hansol Jang, Changwook Jun, Kyunghoon Bae, Hyewon Choi, Stanley Jungkyu Choi, Honglak Lee, Chulmin Yun

机构 * LG AI Research（LG人工智能研究） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL

Comments 10 pages

Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs

Zongjie Li, Daoyuan Wu, Shuai Wang, Zhendong Su

机构 * Hong Kong University of Science and Technology（香港科技大学） ； ETH Zurich（苏黎世联邦理工学院） 纠错

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；SFT(abstract)；分类 cs.AI

Comments In Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security (CCS'25), October 13-17, 2025, Taipei, Taiwan, China. ACM, New York, NY, USA, 15 pages. https://doi.org/10.1145/3719027.3744856

Lessons from Training Grounded LLMs with Verifiable Rewards

Shang Hong Sim, Tej Deep Pala, Vernon Toh, Hai Leong Chieu, Amir Zadeh, Chuan Li, Navonil Majumder, Soujanya Poria

专题命中 指令微调 ：large language model(abstract)；language model(abstract)；instruction tuning(abstract)；分类 cs.CL

Targeted Lexical Injection: Unlocking Latent Cross-Lingual Alignment in Lugha-Llama via Early-Layer LoRA Fine-Tuning

Stanley Ngugi

机构 * Stanley Ngugi（独立研究者） 纠错

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 11 pages, 3 figures, 2 tables. Research on parameter-efficient fine-tuning (PEFT) for low-resource languages (Swahili). Investigates cross-lingual lexical alignment in Lugha-Llama using LoRA and contrastive learning

Passing the Turing Test in Political Discourse: Fine-Tuning LLMs to Mimic Polarized Social Media Comments

. Pazzaglia, V. Vendetti, L. D. Comencini, F. Deriu, V. Modugno

专题命中 指令微调 ：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Loss Functions and Operators Generated by f-Divergences

Vincent Roulet, Tianlin Liu, Nino Vieillard, Michael E. Sander, Mathieu Blondel

机构 * Google DeepMind（谷歌DeepMind） 纠错

专题命中 指令微调 ：language model(abstract)；post-training(abstract)；SFT(abstract)；分类 cs.LG