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

• URL: http://arxiv.org/abs/2604.14389v1
• Date: Wed, 15 Apr 2026 20:06:24 GMT
• Title: BiCon-Gate: Consistency-Gated De-colloquialisation for Dialogue Fact-Checking
• Abstract summary: We propose a conservative rewrite candidate for each response claim via staged de-colloquialisation.<n>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.<n>This gated selection stabilises downstream fact-checking and yields gains in both evidence retrieval and fact verification.
• Score: 9.866690791407464
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• ECHO: A Matched-Contrast Benchmark for Context-Sensitive Turn-Taking in Full-Duplex Dialogue [19.857222937196745]
  We develop diagnostic benchmark for Chinese full spoken dialogue turn-taking pairs pairs examples.<n>We introduce pair accuracy, which requires correct decisions for both members of a pair and assigns no credit to constant-action policies.<n>These findings demonstrate that interruption-only evaluation can distinguish practical turntaking reliability.
  arXiv  Detail & Related papers  (2026-09-15T15:58:48Z)
• From Topical Relevance to Answerability: Entailment Distillation for Conversational Retrieval [24.372303326753535]
  We propose CLEAR, a framework that shifts conversational retrieval from topical relevance to answerability.<n>The core of CLEAR is entailment distillation, which transfers answer-passage entailment supervision into a cross-encoder reranker.<n> CLEAR consistently improves top-ranked precision over strong query-rewriting and dense-retrieval baselines.
  arXiv  Detail & Related papers  (2026-09-03T07:38:36Z)
• Resolving Ambiguity in Composed Image Retrieval via Calibrated Interaction [0.0]
  Composed image retrieval (CIR) searches a corpus with a reference image and a text describing how to modify it.<n>We introduce AmbiCIR, a benchmark and human-validated user simulator that revives the dormant auxiliary and dialogue annotations of CIRR.
  arXiv  Detail & Related papers  (2026-05-23T15:49:16Z)
• More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection [49.07221734365168]
  Hate speech on social media is critical for securing cyberspace, yet relies heavily on automated detection systems.<n>We characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion.<n>We propose the Asymmetric Reasoning via Courtroom Agent DEbate framework to effectively decipher these complex cues.
  arXiv  Detail & Related papers  (2026-03-22T15:46:23Z)
• When Contextual Inference Fails: Cancelability in Interactive Instruction Following [51.2195840589474]
  We introduce Build What I Mean, an interactive benchmark for contextual meaning construction.<n>In BWIM, models must resolve ambiguity by either performing a contextual inference or requesting clarification at a small communication cost.<n>We observe suboptimal strategies, such as partner-blind over-clarification and question-averse guessing under uncertainty.
  arXiv  Detail & Related papers  (2026-03-20T14:46:59Z)
• RECOR: Reasoning-focused Multi-turn Conversational Retrieval Benchmark [20.750773856512662]
  We present a benchmark for reasoning-based conversational information retrieval comprising 707 conversations (2,971 turns) across eleven domains.<n>To ensure quality, our Decomposition-and-Verification framework transforms complex queries into fact-grounded multi-turn dialogues.
  arXiv  Detail & Related papers  (2026-01-09T01:25:46Z)
• Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses [71.34350093068473]
  This paper introduces a new paradigm for generative error correction (GER) framework in audio-visual speech recognition (AVSR)<n>Our framework, DualHyp, empowers a large language model (LLM) to compose independent N-best hypotheses from separate automatic speech recognition (ASR) and visual speech recognition (VSR) models.<n>Our framework attains up to 57.7% error rate gain on the LRS2 benchmark over standard ASR baseline, contrary to single-stream GER approaches that achieve only 10% gain.
  arXiv  Detail & Related papers  (2025-10-15T08:27:16Z)
• Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules [19.673388630963807]
  We formalise the challenge as span-conditioned generation, decomposing each turn into the dialogue history.<n>We introduce a quotation-centric data pipeline that automatically synthesises task-specific dialogues.<n>We propose QuAda, a lightweight training-based method that attaches two bottleneck projections to every attention head.
  arXiv  Detail & Related papers  (2025-05-30T07:06:11Z)
• Localizing Factual Inconsistencies in Attributable Text Generation [74.11403803488643]
  We introduce QASemConsistency, a new formalism for localizing factual inconsistencies in attributable text generation.<n>We show that QASemConsistency yields factual consistency scores that correlate well with human judgments.
  arXiv  Detail & Related papers  (2024-10-09T22:53:48Z)
• High-precision Voice Search Query Correction via Retrievable Speech-text Embedings [13.4015768521113]
  Speech recognition systems can suffer from poor recall for various reasons, such as noisy audio, lack of sufficient training data, etc. Previous work has shown that recall can be improved by retrieving rewrite candidates from a large database of likely, contextually-relevant alternatives to the hypothesis text. We show a relative word error rate (WER) reduction of 6% on utterances whose transcripts appear in the candidate set, without increasing WER on general utterances.
  arXiv  Detail & Related papers  (2024-01-08T20:59:56Z)
• ZeQR: Zero-shot Query Reformulation for Conversational Search [11.644235288057123]
  We introduce a novel Zero-shot Query Reformulation (or Query Rewriting) framework that reformulates queries based on previous dialogue contexts without requiring supervision from conversational search data. Specifically, our framework utilizes language models designed for machine reading comprehension tasks to explicitly resolve two common ambiguities: coreference and omission, in raw queries. It also provides greater explainability and effectively enhances query intent understanding because ambiguities are explicitly and proactively resolved.
  arXiv  Detail & Related papers  (2023-07-18T16:05:25Z)
• End-to-End Page-Level Assessment of Handwritten Text Recognition [69.55992406968495]
  HTR systems increasingly face the end-to-end page-level transcription of a document. Standard metrics do not take into account the inconsistencies that might appear. We propose a two-fold evaluation, where the transcription accuracy and the RO goodness are considered separately.
  arXiv  Detail & Related papers  (2023-01-14T15:43:07Z)
• Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting [56.268862325167575]
  We tackle conversational passage retrieval (ConvPR) with query reformulation integrated into a multi-stage ad-hoc IR system. We propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, standalone, human-understandable queries with a pretrained sequence-tosequence model.
  arXiv  Detail & Related papers  (2020-05-05T14:30:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.