← Search

Shengen Wu

2 accepted papers

2026

ACE: Attribution-Controlled Knowledge Editing for Multi-hop Factual Recall

ICLR 2026poster

LLMs require efficient knowledge editing (KE) to update factual information, yet existing methods exhibit significant performance decay in multi-hop factual recall. This failure is particularly acute when edits involve intermediate implicit subjects within reasoning chains. Through causal analysis,…

Cited by 0SourcecodeScholar
2025

Can GRPO Boost Complex Multimodal Table Understanding?

EMNLP 2025

Existing table understanding methods face challenges due to complex table structures and intricate logical reasoning. While supervised finetuning (SFT) dominates existing research, reinforcement learning (RL), such as Group Relative Policy Optimization (GRPO), has shown promise but struggled with lo