让对话事实核查更准：用智能门控筛选改写语句
BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking
- 分步去口语化+上下文一致性判断，只在有依据时才改写
- 在DialFact上提升检索与验证效果，支持类判断提升显著
- 适合需要精准理解口语对话的场景，如客服、医疗咨询
对话中的自动事实核查面临多轮对话中频繁出现口语化表达但研究不足的问题。为此，我们提出对每个回答主张进行保守性重写，通过分阶段去口语化——结合轻量级表面规范化和限定范围的句内指代消解。随后引入BiCon-Gate，一种语义感知的一致性门控机制，仅当重写候选与对话上下文语义一致时才选用，否则保留原句。该门控策略稳定了下游事实核查性能，在证据检索与事实验证上均取得提升。在DialFact基准测试中，本方法优于多个竞争基线，包括一个单次生成的基于解码器的大语言模型重写方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。