24 citations · 82 across the 50 of their papers we have counts for
3 papers · 1 filter
Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach
Hongyu Cao, Kunpeng Liu, Dongjie Wang +1
Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical infere…
Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
Xinyuan Wang, Dongjie Wang, Wangyang Ying +5
Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers f…
RATT: A Thought Structure for Coherent and Correct LLM Reasoning
Jinghan Zhang, Xiting Wang, Weijieying Ren +3
Large Language Models (LLMs) gain substantial reasoning and decision-making capabilities from thought structures. However, existing methods such as Tree of Thought and Retrieval Au…