# Pardon? Evaluating Conversational Repair in Large Audio-Language Models

arXiv: https://arxiv.org/abs/2601.12973 · HTML: https://mlsanity.com/paper/2601.12973/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 19 Jan 2026.

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

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark](https://mlsanity.com/paper/2410.19168/) (2024)
- [AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension](https://mlsanity.com/paper/2402.07729/) (2024)
- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities](https://mlsanity.com/paper/2406.11768/) (2024)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?](https://mlsanity.com/paper/2405.16908/) (2024)
- [Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering](https://mlsanity.com/paper/2204.09634/) (2022)
- [LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis](https://mlsanity.com/paper/2505.02625/) (2025)
- [Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback](https://mlsanity.com/paper/2403.18349/) (2024)
- [SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks](https://mlsanity.com/paper/2212.10525/) (2022)
- [Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue](https://mlsanity.com/paper/2409.04927/) (2024)
- [C3: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations](https://mlsanity.com/paper/2507.22968/) (2025)
- [VocalBench-DF: A Benchmark for Evaluating Speech LLM Robustness to Disfluency](https://mlsanity.com/paper/2510.15406/) (2025)

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

- [Empathy as Predictive Misalignment Tolerance: A Co-Regulation Framework and the Regime Structure of Dialogue Repair](https://mlsanity.com/paper/2607.15282/) (2026)

## Abstract (arXiv)

Large Audio-Language Models (LALMs) have demonstrated strong performance in spoken question answering (QA), with existing evaluations primarily focusing on answer accuracy and robustness to acoustic perturbations. However, such evaluations implicitly assume that spoken inputs remain semantically answerable, an assumption that often fails in real-world interaction when essential information is missing. In this work, we introduce a repair-aware evaluation setting that explicitly distinguishes between answerable and unanswerable audio inputs. We define answerability as a property of the input itself and construct paired evaluation conditions using a semantic-acoustic masking protocol. Based on this setting, we propose the Evaluability Awareness and Repair (EAR) score, a non-compensatory metric that jointly evaluates task competence under answerable conditions and repair behavior under unanswerable conditions. Experiments on two spoken QA benchmarks across diverse LALMs reveal a consistent gap between answer accuracy and conversational reliability: while many models perform well when inputs are answerable, most fail to recognize semantic unanswerability and initiate appropriate conversational repair. These findings expose a limitation of prevailing accuracy-centric evaluation practices and motivate reliability assessments that treat unanswerable inputs as cues for repair and continued interaction.