# When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models

arXiv: https://arxiv.org/abs/2508.15407 · HTML: https://mlsanity.com/paper/2508.15407/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 21 Aug 2025.

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

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension](https://mlsanity.com/paper/2402.07729/) (2024)
- [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](https://mlsanity.com/paper/1903.10346/) (2019)
- [Words or Vision: Do Vision-Language Models Have Blind Faith in Text?](https://mlsanity.com/paper/2503.02199/) (2025)
- [Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering](https://mlsanity.com/paper/2204.09634/) (2022)
- [Sound Event Detection: A Tutorial](https://mlsanity.com/paper/2107.05463/) (2021)
- [Reducing Distraction in Long-Context Language Models by Focused Learning](https://mlsanity.com/paper/2411.05928/) (2024)
- [On the robustness of multimodal language model towards distractions](https://mlsanity.com/paper/2502.09818/) (2025)

## Built on by (most cited first, 13 of 13)

- [When Audio-LLMs Don't Listen: A Cross-Linguistic Study of Modality Arbitration](https://mlsanity.com/paper/2602.11488/) (2026)
- [When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Models](https://mlsanity.com/paper/2510.00626/) (2025)
- [Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering](https://mlsanity.com/paper/2603.06854/) (2026)
- [Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models](https://mlsanity.com/paper/2606.05161/) (2026)
- [A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models](https://mlsanity.com/paper/2606.17417/) (2026)
- [CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models](https://mlsanity.com/paper/2606.23052/) (2026)
- [Learning to Prefer Reliably: Error-Augmented Emotion Preference Optimization with Calibrated Fusion](https://mlsanity.com/paper/2608.24730/) (2026)
- [When Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removal](https://mlsanity.com/paper/2603.20433/) (2026)
- [Leading-Silence Augmentation and Multi-Stage Synthetic Supervision for the Second MLC-SLM Challenge](https://mlsanity.com/paper/2608.14150/) (2026)
- [Causal Localization of the Refusal Direction in Audio Language Models](https://mlsanity.com/paper/2609.22260/) (2026)
- [Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts](https://mlsanity.com/paper/2609.26986/) (2026)
- [AnchorPrompt: Self-Distilled Soft Prompts for Robust Audio-Language Models](https://mlsanity.com/paper/2610.00706/) (2026)
- [EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference Learning](https://mlsanity.com/paper/2610.13353/) (2026)

## Abstract (arXiv)

Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and text. However, their performance in handling conflicting information between audio and text modalities remains largely unexamined. This paper introduces MCR-BENCH, the first comprehensive benchmark specifically designed to evaluate how LALMs prioritize information when presented with inconsistent audio-text pairs. Through extensive evaluation across diverse audio understanding tasks, we reveal a concerning phenomenon: when inconsistencies exist between modalities, LALMs display a significant bias toward textual input, frequently disregarding audio evidence. This tendency leads to substantial performance degradation in audio-centric tasks and raises important reliability concerns for real-world applications. We further investigate the influencing factors of text bias, and explore mitigation strategies through supervised finetuning, and analyze model confidence patterns that reveal persistent overconfidence even with contradictory inputs. These findings underscore the need for improved modality balance during training and more sophisticated fusion mechanisms to enhance the robustness when handling conflicting multi-modal inputs. The project is available at https://github.com/WangCheng0116/MCR-BENCH.