语言大模型 / LLM - arXivDaily 专题

2602.12158 2026-02-13 cs.LG 89%

SafeNeuron: Neuron-Level Safety Alignment for Large Language Models

SafeNeuron: 大语言模型的神经层面安全对齐

Zhaoxin Wang, Jiaming Liang, Fengbin Zhu, Weixiang Zhao, Junfeng Fang, Jiayi Ji, Handing Wang, Tat-Seng Chua

机构 * Xidian University, Xi'an, China（西安电子科技大学）； Harbin Institute of Technology, Harbin, China（哈尔滨工业大学）； National University of Singapore,Singapore（新加坡国立大学）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；preference optimization(abstract)；分类 cs.LG

AI总结 SafeNeuron通过神经层面安全对齐框架提升模型鲁棒性，减少攻击风险并保持通用能力。

2602.04493 2026-02-05 cs.CL cs.HC 89%

PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM Evaluation

PersoDPO: 通过多LLM评估实现可扩展的偏好优化

Saleh Afzoon, MohammadHossein Ahmadi, Usman Naseem, Amin Beheshti

机构 * School of Computing, Macquarie University（计算机学院，麦考瑞大学）

专题命中后训练与偏好优化：preference optimization(title,abstract)；LLM(title)；large language model(abstract)；language model(abstract)

AI总结 PersoDPO通过多LLM评估实现可扩展的偏好优化，提升对话系统的人格导向和上下文连贯性。

Comments Accepted at WISE 2025 Conference

2601.05075 2026-01-09 cs.CL 89%

SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment

SemPA：通过语义偏好对齐提升大语言模型的句子嵌入

Ziyang Chen, Zhenxuan Huang, Yile Wang, Weiqin Wang, Lu Yin, Hui Huang

机构 * College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）； School of Computer Science and Electronic Engineering, University of Surrey（Surrey大学计算机科学与电子工程学院）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；preference optimization(abstract)；分类 cs.CL

AI总结 SemPA通过语义偏好对齐提升大语言模型的句子嵌入能力，同时保持其生成能力。

2601.02764 2026-01-07 cs.IR cs.AI 89%

Netflix Artwork Personalization via LLM Post-training

通过LLM后训练实现Netflix作品个性化

Hyunji Nam, Sejoon Oh, Emma Kong, Yesu Feng, Moumita Bhattacharya

机构 * Stanford University（斯坦福大学）

专题命中后训练与偏好优化：post-training(title,abstract)；LLM(title)；large language model(abstract)；language model(abstract)

AI总结通过LLM后训练实现Netflix作品个性化推荐，提升用户满意度和参与度。

Comments 6 pages

2601.00647 2026-01-05 cs.CL cs.CE q-bio.QM 89%

Physio-DPO: Aligning Large Language Models with the Protein Energy Landscape to Eliminate Structural Hallucinations

Physio-DPO：将大型语言模型与蛋白质能量景观对齐以消除结构幻觉

QiWei Meng

机构 * Xi’an Jiaotong University（西安交通大学）

专题命中后训练与偏好优化：language model(title,abstract)；large language model(title)；SFT(abstract)；preference optimization(abstract)

AI总结 Physio-DPO通过引入物理感知的目标，将蛋白质语言模型与热力学稳定性对齐，有效减少结构幻觉并提升折叠性。

2409.18541 2025-12-05 cs.AI 89%

Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation

Align$^2$LLaVA: 多模态指令编纂的级联人类与大语言模型偏好对齐

Hongzhe Huang, Jiang Liu, Zhewen Yu, Li Cai, Dian Jiao, Wenqiao Zhang, Siliang Tang, Juncheng Li, Hao Jiang, Haoyuan Li, Yueting Zhuang

机构 * Zhejiang University（浙江大学）； Alibaba（阿里巴巴）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

AI总结 Align$^2$LLaVA通过级联人类与LLM偏好对齐方法，有效压缩多模态指令数据，提升模型性能。

2511.09385 2025-11-18 cs.CL 89%

AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment

Ruibo Deng, Duanyu Feng, Wenqiang Lei

专题命中后训练与偏好优化：language model(title,abstract)；preference optimization(title,abstract)；RLHF(abstract)；分类 cs.CL

Comments AAAI 2026 AIA oral, our code is available at https://github.com/Shiroha-Offical/AMaPO

2511.06023 2025-11-11 cs.CL 89%

Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data

Deng Yixuan, Ji Xiaoqiang

机构 * School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）科学与工程学院）； School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China（香港中文大学（深圳）人工智能学院）； Shenzhen Institute of Artificial Intelligence and Robotics for Society, China（深圳人工智能与机器人研究院）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；RLHF(abstract)；分类 cs.CL

2509.26114 2025-10-01 cs.LG 89%

Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models

Jaesung R. Park, Junsu Kim, Gyeongman Kim, Jinyoung Jo, Sean Choi, Jaewoong Cho, Ernest K. Ryu

机构 * Department of Mathematics, UCLA（UCLA数学系）； Department of Mathematical Sciences, Seoul National University（首尔国立大学数学科学系）； KRAFTON ； Department of Linguistics, Stanford University（斯坦福大学语言学系）； Department of Computer Science and Engineering, Santa Clara University（圣克拉拉大学计算机科学与工程系）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.LG

2509.25509 2025-10-01 cs.LG q-bio.QM 89%

Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimization

Langzhou He, Junyou Zhu, Fangxin Wang, Junhua Liu, Haoyan Xu, Yue Zhao, Philip S. Yu, Qitian Wu

专题命中后训练与偏好优化：foundation model(title,abstract)；preference optimization(title,abstract)；post-training(abstract)；分类 cs.LG

2506.07570 2025-09-22 cs.CV cs.AI 89%

OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization

Yixuan Yang, Zhen Luo, Tongsheng Ding, Junru Lu, Mingqi Gao, Jinyu Yang, Victor Sanchez, Feng Zheng

机构 * Southern University of Science and Technology（南方科技大学）； Shanghai Innovation Institute（上海创新研究院）； University of Warwick（沃林顿大学）

专题命中后训练与偏好优化：LLM(title,abstract)；preference optimization(title,abstract)；SFT(abstract)；分类 cs.AI

2509.08541 2025-09-16 cs.CL 89%

CM-Align: Consistency-based Multilingual Alignment for Large Language Models

Xue Zhang, Yunlong Liang, Fandong Meng, Songming Zhang, Yufeng Chen, Jinan Xu, Jie Zhou

机构 * Key Laboratory of Big Data & Artificial Intelligence in Transportation, Beijing Jiaotong University, Ministry of Education（大数据与人工智能交通运输 key laboratory，北京交通大学，教育部）； School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China（计算机科学与技术学院，北京交通大学，北京，中国）； Pattern Recognition Center, WeChat AI, Tencent Inc, China（模式识别中心，微信AI，腾讯公司，中国）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；preference optimization(abstract)；分类 cs.CL

Comments EMNLP 2025 Findings

2508.14853 2025-08-21 cs.LG 89%

Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

Sajib Biswas, Mao Nishino, Samuel Jacob Chacko, Xiuwen Liu

机构 * Department of Computer Science, Florida State University（计算机科学系，佛罗里达州立大学）； Department of Mathematics, Florida State University（数学系，佛罗里达州立大学）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；RLHF(abstract)；分类 cs.LG

2506.11091 2025-08-21 cs.CL cs.SD eess.AS 89%

Customizing Speech Recognition Model with Large Language Model Feedback

Shaoshi Ling, Guoli Ye

机构 * Microsoft Core AI（微软核心人工智能）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

2507.20000 2025-07-29 cs.AI cs.DL 89%

Matching Game Preferences Through Dialogical Large Language Models: A Perspective

Renaud Fabre, Daniel Egret, Patrice Bellot

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments 28 pages, 1 figure. Published in Applied Sciences

Journal ref Applied Sciences, 2025, 15(15), 8307

2410.05255 2025-07-02 cs.CV cs.LG 89%

Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization

Daoan Zhang, Guangchen Lan, Dong-Jun Han, Wenlin Yao, Xiaoman Pan, Hongming Zhang, Mingxiao Li, Pengcheng Chen, Yu Dong, Christopher Brinton, Jiebo Luo

机构 * University of Rochester（罗切斯特大学）； Purdue University（普渡大学）； Yonsei University（延世大学）； Tencent AI Lab（腾讯AI实验室）； University of Washington（华盛顿大学）

专题命中后训练与偏好优化：SFT(title,abstract)；preference optimization(title,abstract)；post-training(abstract)；分类 cs.LG

2506.23235 2025-07-01 cs.CL 89%

Generalist Reward Models: Found Inside Large Language Models

Yi-Chen Li, Tian Xu, Yang Yu, Xuqin Zhang, Xiong-Hui Chen, Zhongxiang Ling, Ningjing Chao, Lei Yuan, Zhi-Hua Zhou

机构 * National Key Laboratory for Novel Software Technology, Nanjing University, China（国家新型软件技术重点实验室，南京大学，中国）； School of Artificial Intelligence, Nanjing University, China（人工智能学院，南京大学，中国）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

2412.14501 2025-06-27 cs.CL 89%

Do Large Language Models Advocate for Inferentialism?

Yuzuki Arai, Sho Tsugawa

机构 * College of Media Arts, Science and Technology, School of Informatics, University of Tsukuba（筑波大学媒体艺术、科学与技术学院，信息学院）； Institute of Systems and Information Engineering, University of Tsukuba（筑波大学系统与信息工程研究所）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；RLHF(abstract)；分类 cs.CL

2503.10093 2025-06-17 cs.CL 89%

Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling

Qiyuan Deng, Xuefeng Bai, Kehai Chen, Yaowei Wang, Liqiang Nie, Min Zhang

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；preference optimization(abstract)；分类 cs.CL

2402.11827 2025-06-17 cs.IR cs.CL 89%

Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation

Chanwoong Yoon, Gangwoo Kim, Byeongguk Jeon, Sungdong Kim, Yohan Jo, Jaewoo Kang

机构 * Korea University（韩国大学）； KAIST AI（韩国科学技术院人工智能研究中心）； Seoul National University（首尔国立大学）； AIGEN Sciences（AIGEN科学）

专题命中后训练与偏好优化：language model(title,abstract)；large language model(title)；preference optimization(abstract)；prompting(abstract)

Comments NAACL 2025 (findings)

2506.08643 2025-06-11 cs.CL 89%

MEMETRON: Metaheuristic Mechanisms for Test-time Response Optimization of Large Language Models

Son The Nguyen, Theja Tulabandhula

机构 * Department of Information and Decision Sciences University of Illinois Chicago（信息与决策科学系伊利诺伊大学香槟分校）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

2410.15639 2025-06-11 cs.CL 89%

Can Large Language Models Invent Algorithms to Improve Themselves?: Algorithm Discovery for Recursive Self-Improvement through Reinforcement Learning

Yoichi Ishibashi, Taro Yano, Masafumi Oyamada

机构 * NEC Corporation（日本电报电话株式会社）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；preference optimization(abstract)；分类 cs.CL

Comments Accepted at NAACL 2025 (main)

2506.06800 2025-06-10 cs.CL 89%

On the Adaptive Psychological Persuasion of Large Language Models

Tianjie Ju, Yujia Chen, Hao Fei, Mong-Li Lee, Wynne Hsu, Pengzhou Cheng, Zongru Wu, Zhuosheng Zhang, Gongshen Liu

机构 * Shanghai Jiao Tong University（上海交通大学）； National University of Singapore（新加坡国立大学）； Sichuan University（四川大学）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；preference optimization(abstract)；分类 cs.CL

Comments Working in progress

2505.23540 2025-05-30 cs.CL 89%

Probability-Consistent Preference Optimization for Enhanced LLM Reasoning

Yunqiao Yang, Houxing Ren, Zimu Lu, Ke Wang, Weikang Shi, Aojun Zhou, Junting Pan, Mingjie Zhan, Hongsheng Li

机构 * CUHK MMLab（香港中文大学MML实验室）； SenseTime Research（商汤科技研究院）； CPII under InnoHK（创新香港下的CPII）； Shanghai AI Laboratory（上海人工智能实验室）； Zhiyuan College, SJTU（上海交通大学智远学院）

专题命中后训练与偏好优化：preference optimization(title,abstract)；LLM(title)；large language model(abstract)；language model(abstract)

Comments 14 pages, to be published in ACL 2025 findings

2402.15481 2025-05-27 cs.CL cs.CY 89%

Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency

Yiran Liu, Ke Yang, Zehan Qi, Xiao Liu, Yang Yu, ChengXiang Zhai

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

2411.06790 2025-05-23 cs.CY cs.CL cs.HC 89%

Large-scale moral machine experiment on large language models

Muhammad Shahrul Zaim bin Ahmad, Kazuhiro Takemoto

机构 * Department of Bioscience and Bioinformatics, Kyushu Institute of Technology（九州工科大学生物科学与生物信息学系）； Faculty of Engineering and Technology, Multimedia University（多媒体大学工程与技术学院）； Data Science and AI Research Center, Kyushu Institute of Technology（九州工科大学数据科学与人工智能研究中心）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

Comments 21 pages, 6 figures

Journal ref PLoS One 20, e0322776 (2025)

2406.14449 2025-05-21 cs.AI 89%

APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking

Can Jin, Hongwu Peng, Shiyu Zhao, Zhenting Wang, Wujiang Xu, Ligong Han, Jiahui Zhao, Kai Zhong, Sanguthevar Rajasekaran, Dimitris N. Metaxas

机构 * Rutgers University（新泽西罗格斯大学）； University of Connecticut（康涅狄格大学）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；preference optimization(abstract)；分类 cs.AI

2505.03209 2025-05-07 cs.LG 89%

DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning

Borui Wang, Kathleen McKeown, Rex Ying

机构 * Department of Computer Science Columbia University（哥伦比亚大学计算机科学系）

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.LG

2504.01735 2025-04-03 cs.CV cs.AI 89%

AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization

Chaohu Liu, Tianyi Gui, Yu Liu, Linli Xu

专题命中后训练与偏好优化：language model(title,abstract)；preference optimization(title,abstract)；large language model(abstract)；分类 cs.AI

2502.14669 2025-02-26 cs.CL 89%

AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO

Alan Dao, Dinh Bach Vu

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；SFT(abstract)；分类 cs.CL

1. 后训练与偏好优化 4541 篇

SafeNeuron: Neuron-Level Safety Alignment for Large Language Models

PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM Evaluation

SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment

Netflix Artwork Personalization via LLM Post-training

Physio-DPO: Aligning Large Language Models with the Protein Energy Landscape to Eliminate Structural Hallucinations

Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation

AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment

Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data

Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models

Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimization

OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization

CM-Align: Consistency-based Multilingual Alignment for Large Language Models

Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

Customizing Speech Recognition Model with Large Language Model Feedback

Matching Game Preferences Through Dialogical Large Language Models: A Perspective

Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization

Generalist Reward Models: Found Inside Large Language Models

Do Large Language Models Advocate for Inferentialism?

Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling

Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation

MEMETRON: Metaheuristic Mechanisms for Test-time Response Optimization of Large Language Models

Can Large Language Models Invent Algorithms to Improve Themselves?: Algorithm Discovery for Recursive Self-Improvement through Reinforcement Learning

On the Adaptive Psychological Persuasion of Large Language Models

Probability-Consistent Preference Optimization for Enhanced LLM Reasoning

Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency

Large-scale moral machine experiment on large language models

APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking

DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning

AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization

AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO