Metraipolis › archive › dc_17554cdf6a0e

DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents — arXiv:2610.21561

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21561
License (as archived)
CC0-1.0
Archived
2026-10-16T09:24:22.548Z
SHA-256 of the archived text
a1dd4b5188994391c4b9fdfebffcbdc4e029322cc6dc26a0cb6d80fc4fa59c43
Stable URL of this page
https://metraipolis.com/documento/dc_17554cdf6a0e

How to cite

DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents — arXiv:2610.21561 — arXiv (en), https://arxiv.org/abs/2610.21561 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_17554cdf6a0e (Metraipolis archive dc_17554cdf6a0e, sha256 a1dd4b5188994391c4b9fdfebffcbdc4e029322cc6dc26a0cb6d80fc4fa59c43)
BibTeX
@misc{dc17554cdf6a0e,
  title = {DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents — arXiv:2610.21561},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21561},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_17554cdf6a0e; sha256 a1dd4b5188994391c4b9fdfebffcbdc4e029322cc6dc26a0cb6d80fc4fa59c43},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21561. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic. While factual hallucination has received extensive attention, a different failure mode has been overlooked: procedural hallucination, in which an agent produces individually fluent and factually plausible utterances while deviating from the intended conversational process. We introduce DialFork, the first benchmark to measure this failure mode on raw dialogue text. DialFork is built by forking conformant dialogues at controlled turn positions and injecting one of four hallucination types, yielding 36,278 dialogues across 24 tasks in 12 domains; 30 human annotators validate the construction. We define three evaluation tasks that characterize procedural deviation at three granularities: how far a set of dialogues deviates from conformant ones (monitoring deployed agents), how far a single dialogue does (procedural retrieval), and at which turn a dialogue first goes off-track (real-time guardrails). For the first two, we propose dialog-flow-aware metrics, FlowKL and FlowScore, that compare dialogues by how they unfold rather than their content. At the dialogue level, FlowScore significantly outperforms all baselines across seven encoders, showing that semantic similarity is no substitute for procedural similarity. We release DialFork under the MIT license at this https URL , hoping the community will measure conversational process alongside content.

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); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.21561 — 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 2026-10-16T08:44:17.966Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).