arXiv cs.AI· Yuhang Dong, Jinghong Li, Xinyue Wang, Yuanning Cui·· 15 小时前AI 评分31
SEAC：经验自适应的主动事实核查“停止或澄清”决策
Stop or Clarify? Experience-Conditioned Active Fact Verification
AI 导读
研究提出 SEAC（Sequential Experience-Adaptive Clarification），用一个轻量级证据获取策略包裹固定核查器，依据停止风险与历史轨迹中的澄清效用估计，仅在得分超过动作成本与决策阈值时请求澄清。
正文 · 原文
Abstract:Fact-verification benchmarks score the final label, while an interactive verifier must first decide whether the available evidence is sufficient. We focus on that intermediate Stop-or-Clarify Decision. Uncertainty alone is insufficient, because the benefit of another evidence-acquisition step is unknown before the step is taken. Sequential Experience-Adaptive Clarification (SEAC) wraps a fixed verifier with a lightweight evidence-acquisition policy. For each claim, SEAC retrieves evidence, runs the verifier, forms a label-free decision state, and combines stop risk with an observational clarification-utility estimate from earlier executed trajectories. Clarification is requested only when this score exceeds the action cost and decision threshold. On SciFact, LIAR, and FEVER, SEAC improves mean accuracy and macro-F1 over the compared fact-verification and active-retrieval baselines. Equal-budget and formula-level diagnostics support selective clarification as a contributor to the gain, while the small SciFact split leaves its paired improvement inconclusive.
| Subjects: | Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2610.34941 [cs.AI] |
| (or arXiv:2610.34941v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34941 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuhang Dong [view email]
[v1]
Mon, 26 Oct 2026 07:08:26 UTC (2,016 KB)
来源：arXiv cs.AI · arxiv.org