Metraipolis › archive › dc_83be65008eaf
PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs — arXiv:2610.10455
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10455
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:12:09.151Z
- SHA-256 of the archived text
9e84fe9be744b43d1c43bda4c8f3f3c2e93db0e3feb28e024dce569bbd77e1f0- Stable URL of this page
https://metraipolis.com/documento/dc_83be65008eaf
How to cite
PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs — arXiv:2610.10455 — arXiv (en), https://arxiv.org/abs/2610.10455 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_83be65008eaf (Metraipolis archive dc_83be65008eaf, sha256 9e84fe9be744b43d1c43bda4c8f3f3c2e93db0e3feb28e024dce569bbd77e1f0)
BibTeX
@misc{dc83be65008eaf,
title = {PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs — arXiv:2610.10455},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10455},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_83be65008eaf; sha256 9e84fe9be744b43d1c43bda4c8f3f3c2e93db0e3feb28e024dce569bbd77e1f0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10455. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 more frequent belief updates along the reasoning trajectory. We further find that properties of the hallucinated prompt contain substantial predictive signal for successful recovery, with a lightweight predictor achieving an AUROC of 0.847. These findings provide a behavioral view of post-hallucination reasoning, characterizing how LLMs resolve erroneous context and when successful recovery is likely to occur. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.10455 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T10:14:06.184Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).