语言大模型 / LLM - arXivDaily 专题

2509.06759 2025-09-09 cs.LG cs.AI 91%

Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization

Thanh Thi Nguyen, Campbell Wilson, Janis Dalins

机构 * AiLECS Lab, Monash University Melbourne, Australia（墨尔本大学AiLECS实验室，澳大利亚）； AiLECS Lab, Monash University, Australia ICMEC Australia, Sydney, Australia（墨尔本大学AiLECS实验室，澳大利亚 ICMEC澳大利亚，悉尼，澳大利亚）

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

Comments Accepted for publication in the Proceedings of the 8th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI 2025)

2509.05318 2025-09-09 cs.CR cs.AI 85%

Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models

Zuquan Peng, Jianming Fu, Lixin Zou, Li Zheng, Yanzhen Ren, Guojun Peng

机构 * Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University（航天信息安全部门、教育部、网络安全科学与工程学院、武汉大学）

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

Comments 13 pages, 9 figures, 8 tables, journal

Journal ref Neural Networks 193(2026) 108025

2504.15477 2025-09-09 cs.LG 85%

In-context Ranking Preference Optimization

Junda Wu, Rohan Surana, Zhouhang Xie, Yiran Shen, Yu Xia, Tong Yu, Ryan A. Rossi, Prithviraj Ammanabrolu, Julian McAuley

机构 * UC San Diego（加州大学圣迭戈分校）； Adobe Research（Adobe研究）

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

Comments 10 pages

2504.18026 2025-09-09 cs.LG cs.AI 81%

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization

Emiliano Penaloza, Tianyue H. Zhang, Laurent Charlin, Mateo Espinosa Zarlenga

机构 * Mila - Québec AI Institute（魁北克人工智能研究所）； University of Cambridge（剑桥大学）

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

2509.05863 2025-09-09 cs.CL 79%

LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization

Luis Felipe Chary, Miguel Arjona Ramirez

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

2507.02949 2025-09-09 cs.CL 77%

RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence

Vipula Rawte, Rajarshi Roy, Gurpreet Singh, Danush Khanna, Yaswanth Narsupalli, Basab Ghosh, Abhay Gupta, Argha Kamal Samanta, Aditya Shingote, Aadi Krishna Vikram, Vinija Jain, Aman Chadha, Amit Sheth, Amitava Das

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

2509.02333 2025-09-09 cs.CL cs.AI cs.LG 75%

DCPO: Dynamic Clipping Policy Optimization

Shihui Yang, Chengfeng Dou, Peidong Guo, Kai Lu, Qiang Ju, Fei Deng, Rihui Xin

专题命中后训练与偏好优化：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI、cs.LG

2509.01563 2025-09-09 cs.CV 75%

Kwai Keye-VL 1.5 Technical Report

Biao Yang, Bin Wen, Boyang Ding, Changyi Liu, Chenglong Chu, Chengru Song, Chongling Rao, Chuan Yi, Da Li, Dunju Zang, Fan Yang, Guorui Zhou, Guowang Zhang, Han Shen, Hao Peng, Haojie Ding, Hao Wang, Haonan Fan, Hengrui Ju, Jiaming Huang, Jiangxia Cao, Jiankang Chen, Jingyun Hua, Kaibing Chen, Kaiyu Jiang, Kaiyu Tang, Kun Gai, Muhao Wei, Qiang Wang, Ruitao Wang, Sen Na, Shengnan Zhang, Siyang Mao, Sui Huang, Tianke Zhang, Tingting Gao, Wei Chen, Wei Yuan, Xiangyu Wu, Xiao Hu, Xingyu Lu, Yi-Fan Zhang, Yiping Yang, Yulong Chen, Zeyi Lu, Zhenhua Wu, Zhixin Ling, Zhuoran Yang, Ziming Li, Di Xu, Haixuan Gao, Hang Li, Jing Wang, Lejian Ren, Qigen Hu, Qianqian Wang, Shiyao Wang, Xinchen Luo, Yan Li, Yuhang Hu, Zixing Zhang

机构 * Keye Team, Kuaishou Group（快手集团Keye团队）

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

Comments Github page: https://github.com/Kwai-Keye/Keye

2506.07963 2025-09-09 cs.AI cs.CL cs.CV 73%

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards

Jixiang Hong, Yiran Zhang, Guanzhong Wang, Yi Liu, Ji-Rong Wen, Rui Yan

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（计算机科学学院）； Baidu Inc.（百度公司）； School of Computer Science, Wuhan University（武汉大学计算机学院）

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

2509.06870 2025-09-09 cs.CL 70%

The Majority is not always right: RL training for solution aggregation

Wenting Zhao, Pranjal Aggarwal, Swarnadeep Saha, Asli Celikyilmaz, Jason Weston, Ilia Kulikov

机构 * FAIR at Meta（Meta旗下的FAIR）

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

1. 后训练与偏好优化 10 篇

Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization

Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models

In-context Ranking Preference Optimization

Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization

LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization

RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence

DCPO: Dynamic Clipping Policy Optimization

Kwai Keye-VL 1.5 Technical Report

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards

The Majority is not always right: RL training for solution aggregation