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

arXiv: https://arxiv.org/abs/2604.14389 · HTML: https://mlsanity.com/paper/2604.14389/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 31 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Automated Fact Checking: Task formulations, methods and future directions](https://mlsanity.com/paper/1806.07687/) (2018)
- [DialFact: A Benchmark for Fact-Checking in Dialogue](https://mlsanity.com/paper/2110.08222/) (2021)
- [Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations](https://mlsanity.com/paper/2102.10073/) (2021)
- [Calibrating Language Models with Adaptive Temperature Scaling](https://mlsanity.com/paper/2409.19817/) (2024)
- [Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends](https://mlsanity.com/paper/2407.21489/) (2024)
- [From Chaos to Clarity: Claim Normalization to Empower Fact-Checking](https://mlsanity.com/paper/2310.14338/) (2023)
- [Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking](https://mlsanity.com/paper/2501.10860/) (2025)
- [Automated Fact-Checking in Dialogue: Are Specialized Models Needed?](https://mlsanity.com/paper/2311.08195/) (2023)
- [IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark for LLMs](https://mlsanity.com/paper/2411.07466/) (2024)
- [FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers](https://mlsanity.com/paper/2301.03319/) (2023)
- [Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation](https://mlsanity.com/paper/2503.16043/) (2025)

## Abstract (arXiv)

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.