BiCon-Gate：基于一致性门控的对话事实核查去口语化处理
BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking
AI总结：
本文提出BiCon-Gate，通过语义感知的一致性门控选择改写候选，提升对话事实核查的证据检索与验证效果，尤其在SUPPORTS任务上表现突出。
摘要：
对话中的自动事实核查涉及多轮对话，其中口语化语言频繁但研究不足。为填补这一空白，我们提出一种保守的改写候选生成方法，结合轻量级表面规范化与作用域内声明核心指代解析。随后引入BiCon-Gate，一种语义感知的一致性门控，仅在对话上下文语义支持时选择改写候选，否则回退到原始声明。这种门控选择稳定了下游事实核查，并在证据检索和事实验证方面取得收益。在DialFact基准测试中，我们的方法提升了检索和验证性能，尤其在SUPPORTS任务上表现突出，并优于包括基于解码器的一次性LLM改写在内的竞争基线。
英文摘要：
Automated fact-checking in dialogue involves multi-turn conversations where colloquial language is frequent yet understudied. To address this gap, we propose a conservative rewrite candidate for each response claim via staged de-colloquialisation, combining lightweight surface normalisation with scoped in-claim coreference resolution. We then introduce BiCon-Gate, a semantics-aware consistency gate that selects the rewrite candidate only when it is semantically supported by the dialogue context, otherwise falling back to the original claim. This gated selection stabilises downstream fact-checking and yields gains in both evidence retrieval and fact verification. On the DialFact benchmark, our approach improves retrieval and verification, with particularly strong gains on SUPPORTS, and outperforms competitive baselines, including a decoder-based one-shot LLM rewrite that attempts to perform all de-colloquialisation steps in a single pass.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
