PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
[Przetwarzanie języka] Autorzy: Linghao Meng, Feng He, Xuan Yang i 5 więcej
Hallucinated information can propagate through multi-stage LLM systems and become part of the context for subsequent reasoning. Existing studies of post-hallucination reasoning (PHR) mainly characterize changes in final outcomes and aggregate reasoning dynamics, leaving how models resolve hallucinated premises at the response level insufficiently understood. In this work, we introduce PHRBench, a controlled benchmark for behaviorally structured PHR across four domains and 18 large language models. PHRBench characterizes each reasoning trajectory independently of final-answer correctness through Hallucination Compliance, Hallucination Avoidance, and Heuristic Correction, and defines an insightful trajectory as successful correction that ultimately reaches the correct answer. Across 4820 controlled instances, we find that successful recovery remains relatively rare and is associated with …
- Kategoria arxiv
- cs.CL
- Kategoria
- Przetwarzanie języka