Preprint
Jul 2026
Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM
This work conducts a fine-grained analysis of hallucinations arising in LLM reasoning and finds that the reasoning traces are particularly prone to Context-Sensitive Factual Hallucinations: cases where the model actually has the relevant knowledge, yet makes factual errors due to contextual interference during reasoning.
Xiaomeng Hu, Jiaqi Hu, Hao Chen et al.
· 0 citations