大模型对齐与安全

Cross-Modal Safety Alignment: Is textual unlearning all you need?

Trishna Chakraborty, Erfan Shayegani, Zikui Cai, Nael Abu-Ghazaleh, M. Salman Asif, Yue Dong, Amit K. Roy-Chowdhury, Chengyu Song

机构 * University of California, Riverside（加州大学河滨分校） 纠错

专题命中 偏好对齐 ：alignment(title,abstract)；safety(title,abstract)；RLHF(abstract)；分类 cs.CL、cs.LG

Comments Accepted by EMNLP 2024 Findings

Hierarchical Alignment: Surgical Fine-Tuning via Functional Layer Specialization in Large Language Models

Yukun Zhang, Qi Dong

机构 * The Chinese University of Hong Kong（香港中文大学） ； Fudan University（复旦大学） 纠错

专题命中 偏好对齐 ：alignment(title,abstract)；DPO(abstract)；分类 cs.CL、cs.AI

DPO-Tuned Large Language Models for Segmentation in Simultaneous Speech Translation

Zeyu Yang, Satoshi Nakamura

专题命中 偏好对齐 ：DPO(title,abstract)；alignment(abstract)；分类 cs.CL

Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment

Samuel Yeh, Sharon Li

专题命中 偏好对齐 ：alignment(title,abstract)；分类 cs.CL、cs.AI

Comments NeurIPS 2025

COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences

Yixin Liu, Argyris Oikonomou, Weiqiang Zheng, Yang Cai, Arman Cohan

机构 * Yale University（耶鲁大学） ； Allen Institute for AI（人工智能研究院） 纠错

专题命中 偏好对齐 ：alignment(abstract)；RLHF(abstract)；分类 cs.CL、cs.AI、cs.LG

Learning Dynamics of VLM Finetuning

Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang

机构 * Sun Yat-sen University（中山大学） ； X-Era AI Lab（X-Era人工智能实验室） 纠错

专题命中 偏好对齐 ：alignment(abstract)；DPO(abstract)；分类 cs.AI、cs.LG

Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval

Eric He, Akash Gupta, Adian Liusie, Vatsal Raina, Piotr Molenda, Shirom Chabra, Vyas Raina

机构 * University of Cambridge（剑桥大学） ； Apta 纠错

专题命中 偏好对齐 ：alignment(abstract)；分类 cs.LG

Unspoken Hints: Accuracy Without Acknowledgement in LLM Reasoning

Arash Marioriyad, Shaygan Adim, Nima Alighardashi, Mahdieh Soleymani Banghshah, Mohammad Hossein Rohban

专题命中 偏好对齐 ：RLHF(abstract)；分类 cs.CL

Comments 5 Pages, 4 Figures, 4 Tables

Journal ref 39th Conference on Neural Information Processing Systems, 2025, Workshop: Reliable ML from Unreliable Data