BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking

2026-04-15

AI Summary

This work addresses the challenge that conversational fact-checking systems face due to informal, colloquial expressions in spoken dialogue, which degrade evidence retrieval and claim verification performance. The authors propose a staged disfluency removal approach that combines lightweight surface normalization with scope-constrained coreference resolution to generate conservative rewrite candidates. To preserve semantic fidelity, they introduce a semantics-aware consistency gating mechanism that adopts a rewritten claim only when strongly supported by the conversational context; otherwise, the original utterance is retained. Evaluated on the DialFact benchmark, this method significantly improves both evidence retrieval and fact verification accuracy, notably outperforming strong baselines—including end-to-end large language model–based rewriting—particularly on SUPPORTS-class claims.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Reasoning with Beliefs

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• dialogue fact-checking
• colloquial language
• de-colloquialisation
• consistency
• fact verification

Innovation

• de-colloquialisation
• consistency gating
• dialogue fact-checking
• semantic consistency
• coreference resolution