When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908497110630400 |
|---|---|
| author | Wang, Cheng Deng, Gelei Yang, Xianglin Qiu, Han Zhang, Tianwei |
| author_facet | Wang, Cheng Deng, Gelei Yang, Xianglin Qiu, Han Zhang, Tianwei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15407 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models Wang, Cheng Deng, Gelei Yang, Xianglin Qiu, Han Zhang, Tianwei Computation and Language Artificial Intelligence 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. |
| title | When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2508.15407 |