DialFork:評估對話智能體程序性幻覺,超越事實性評估
DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents
DialFork 提出一套基準及流程感知評測指標,評估對話智能體偏離預期對話流程的程序性幻覺,而非只比較內容相似度。基準包含 24 項任務、12 個領域的 36,278 段對話,並由 30 名人類標註員驗證。研究亦提出 FlowKL 和 FlowScore;FlowScore 在七種編碼器上均顯著勝過所有基線,DialFork 以 MIT 授權釋出。
Published on Oct 15
Authors:
,
,
,
,
,
Abstract
DialFork introduces a benchmark and flow-aware metrics to detect procedural hallucinations in conversational agents by measuring dialogue-level process deviation rather than content similarity.
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 https://github.com/idiap/dialfork, hoping the community will measure conversational process alongside content.
View arXiv page View PDF GitHub Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.21561 in a model README.md to link it from this page.
Datasets citing this paper 1
DialFork/dialfork
Viewer • Updated about 19 hours ago • 36.3k • 99
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.21561 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co