# Improving Bot Response Contradiction Detection via Utterance Rewriting

arXiv: https://arxiv.org/abs/2207.11862 · HTML: https://mlsanity.com/paper/2207.11862/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 25 Jul 2022.

## Builds on (most cited first, 18 of 18)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Recipes for Safety in Open-domain Chatbots](https://mlsanity.com/paper/2010.07079/) (2020)
- [Dialogue Natural Language Inference](https://mlsanity.com/paper/1811.00671/) (2018)
- [Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills](https://mlsanity.com/paper/2004.08449/) (2020)
- [The Fact Extraction and VERification (FEVER) Shared Task](https://mlsanity.com/paper/1811.10971/) (2018)
- [Coreference Resolution as Query-based Span Prediction](https://mlsanity.com/paper/1911.01746/) (2019)
- [PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning](https://mlsanity.com/paper/2006.16779/) (2020)
- [I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling](https://mlsanity.com/paper/2012.13391/) (2020)
- [Improving Multi-turn Dialogue Modelling with Utterance ReWriter](https://mlsanity.com/paper/1906.07004/) (2019)
- [GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue](https://mlsanity.com/paper/1909.12086/) (2019)
- [Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations](https://mlsanity.com/paper/2008.12348/) (2020)
- [On Generalization in Coreference Resolution](https://mlsanity.com/paper/2109.09667/) (2021)
- [CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues](https://mlsanity.com/paper/2105.09914/) (2021)
- [Alquist 4.0: Towards Social Intelligence Using Generative Models and Dialogue Personalization](https://mlsanity.com/paper/2109.07968/) (2021)
- [Filling Conversation Ellipsis for Better Social Dialog Understanding](https://mlsanity.com/paper/1911.10776/) (2019)

## Built on by (most cited first, 4 of 4)

- [Controllable Mixed-Initiative Dialogue Generation through Prompting](https://mlsanity.com/paper/2305.04147/) (2023)
- [ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models](https://mlsanity.com/paper/2311.09182/) (2023)
- [ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI](https://mlsanity.com/paper/2401.15471/) (2024)
- [EventChat: Implementation and user-centric evaluation of a large language model-driven conversational recommender system for exploring leisure events in an SME context](https://mlsanity.com/paper/2407.04472/) (2024)

## Abstract (arXiv)

Though chatbots based on large neural models can often produce fluent responses in open domain conversations, one salient error type is contradiction or inconsistency with the preceding conversation turns. Previous work has treated contradiction detection in bot responses as a task similar to natural language inference, e.g., detect the contradiction between a pair of bot utterances. However, utterances in conversations may contain co-references or ellipsis, and using these utterances as is may not always be sufficient for identifying contradictions. This work aims to improve the contradiction detection via rewriting all bot utterances to restore antecedents and ellipsis. We curated a new dataset for utterance rewriting and built a rewriting model on it. We empirically demonstrate that this model can produce satisfactory rewrites to make bot utterances more complete. Furthermore, using rewritten utterances improves contradiction detection performance significantly, e.g., the AUPR and joint accuracy scores (detecting contradiction along with evidence) increase by 6.5% and 4.5% (absolute increase), respectively.