# "Mm, Wat?" Detecting Other-initiated Repair Requests in Dialogue

arXiv: https://arxiv.org/abs/2510.24628 · HTML: https://mlsanity.com/paper/2510.24628/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 45 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 6 of 6)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue](https://mlsanity.com/paper/2004.06871/) (2020)
- [RobBERT: a Dutch RoBERTa-based Language Model](https://mlsanity.com/paper/2001.06286/) (2020)
- [Feature Synergy, Redundancy, and Independence in Global Model Explanations using SHAP Vector Decomposition](https://mlsanity.com/paper/2107.12436/) (2021)
- [No that's not what I meant: Handling Third Position Repair in Conversational Question Answering](https://mlsanity.com/paper/2307.16689/) (2023)
- [Multimodal Contextual Dialogue Breakdown Detection for Conversational AI Models](https://mlsanity.com/paper/2404.08156/) (2024)

## Built on by (most cited first, 1 of 1)

- [Do Visual Features Improve Other-Initiated Repair Detection? A Dyadic Multimodal Approach](https://mlsanity.com/paper/2607.23845/) (2026)

## Abstract (arXiv)

Maintaining mutual understanding is a key component in human-human conversation to avoid conversation breakdowns, in which repair, particularly Other-Initiated Repair (OIR, when one speaker signals trouble and prompts the other to resolve), plays a vital role. However, Conversational Agents (CAs) still fail to recognize user repair initiation, leading to breakdowns or disengagement. This work proposes a multimodal model to automatically detect repair initiation in Dutch dialogues by integrating linguistic and prosodic features grounded in Conversation Analysis. The results show that prosodic cues complement linguistic features and significantly improve the results of pretrained text and audio embeddings, offering insights into how different features interact. Future directions include incorporating visual cues, exploring multilingual and cross-context corpora to assess the robustness and generalizability.