Metraipolis › archive › dc_01e36233f221
From Twisted Facts to Rogue Agents: Can LLMs Reliably Detect Multi-Dimensional Hallucinations? — arXiv:2611.08231
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08231
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:43:15.395Z
- SHA-256 of the archived text
fcd3075027f7b7ca61d2554ed64808878fa65411243bf5c8f10cf5c4c74fda8d- Stable URL of this page
https://metraipolis.com/documento/dc_01e36233f221
How to cite
From Twisted Facts to Rogue Agents: Can LLMs Reliably Detect Multi-Dimensional Hallucinations? — arXiv:2611.08231 — arXiv (en), https://arxiv.org/abs/2611.08231 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01e36233f221 (Metraipolis archive dc_01e36233f221, sha256 fcd3075027f7b7ca61d2554ed64808878fa65411243bf5c8f10cf5c4c74fda8d)
BibTeX
@misc{dc01e36233f221,
title = {From Twisted Facts to Rogue Agents: Can LLMs Reliably Detect Multi-Dimensional Hallucinations? — arXiv:2611.08231},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08231},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01e36233f221; sha256 fcd3075027f7b7ca61d2554ed64808878fa65411243bf5c8f10cf5c4c74fda8d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08231. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are widely used for information access, content production, and agent-based task execution, but their outputs remain vulnerable to subtle, high-risk hallucinations. To systematically evaluate and advance post-generation hallucination detection, we introduce HaluCheck, a large-scale, bilingual benchmark comprising over 42k instances spanning both factual hallucinations in text and faithfulness hallucinations in agent trajectories. HaluCheck features fine-grained, multi-level annotations for detection, localization, and correction, covering different tasks and perturbation degrees. Experiments on fourteen LLMs reveal that, while models show basic sample-level detection ability, they struggle with fine-grained localization, correction, and agent hallucination detection. Further analysis demonstrates that thinking, web search, and supervised fine-tuning each offer partial improvements, but none fully solve the problem. HaluCheck thus provides a solid basis for benchmarking and diagnosing LLM reliability across text and agent scenarios. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.08231 — 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 2026-11-06T14:18:57.592Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).