1.5k citations · 2k across the 57 of their papers we have counts for
5 papers · 1 filter
CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation
Chenlu Ding, Jiancan Wu, Yanchen Luo +4
Multimodal large language models (MLLMs) can reproduce sensitive, copyrighted, or unsafe information from their training data. Effective unlearning must remove target information w…
Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning
Chenlu Ding, Jiancan Wu, Yanchen Luo +3
Large language models (LLMs) often fail to reason under temporal cutoffs: when prompted to answer from the standpoint of an earlier time, they exploit knowledge that became availab…
Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging
Jiabei Liu, Wenyu Mao, Junfei Tan +4
Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for…
Unified Parameter-Efficient Unlearning for LLMs
Chenlu Ding, Jiancan Wu, Yancheng Yuan +5
The advent of Large Language Models (LLMs) has revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks. Fin…
-DPO: Direct Preference Optimization with Dynamic
Junkang Wu, Yuexiang Xie, Zhengyi Yang +5
Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO…