paper-with-me

홈 › Papers

DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models

2026-03-17 · Jiaqi Xiong, Yunjia Qi, Qi Cao, Yu Zheng, Yutong Zhang, Ziteng Wang, Ruofan Liao, Weisheng Xu, Sichen Liu arxiv

Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether these models genuinely process acoustic signals or rely on text-based semantic inference. To systematically study this question, we introduce DEAF (Diagnostic Evaluation of Acoustic Faithfulness), a benchmark of over 2,700 conflict stimuli spanning three acoustic dimensions: emotional prosody, background sounds, and speaker identity. Then, we design a controlled multi-level evaluation framework that progressively increases textual influence, ranging from semantic conflicts in the content to misleading prompts and their combination, allowing us to disentangle content-driven bias from prompt-induced sycophancy. We further introduce diagnostic metrics to quantify model reliance on textual cues over acoustic signals. Our evaluation of seven Audio MLLMs reveals a consistent pattern of text dominance: models are sensitive to acoustic variations, yet predictions are predominantly driven by textual inputs, revealing a gap between high performance on standard speech benchmarks and genuine acoustic understanding.

📄 PDF Abstract BibTeX arXiv:2603.18048

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Causal Lens for Evaluating Faithfulness Metrics

2025-02-26 · Kerem Zaman, Shashank Srivastava

Large Language Models (LLMs) offer natural language explanations as an alternative to feature attribution methods for model interpretability. However, despite their plausibility, they may not reflect the model's internal…

Decision MakingFact CheckingModel EditingObject Counting

A Comparative Study of Faithfulness Metrics for Model Interpretability Methods

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Interpretable methods to reveal the internal reasoning processes behind machine learning models have attracted increasing attention in recent years. To quantify the extent to which the identified interpretations truly re…

Decision Making

Towards a Phonology-Informed Evaluation of Multilingual TTS

2026-07-02 · Sneha Ray Barman, Neeraj Kumar Sharma, Shakuntala Mahanta arxiv

Neural TTS systems can sound natural across languages, but naturalness does not guarantee the preservation of sound contrasts that distinguish words from their grammatical forms. Standard metrics like MOS do not test for…

A Comparative Study of Faithfulness Metrics for Model Interpretability Methods

2022-04-12 · ACL 2022 5 · Chun Sik Chan, Huanqi Kong, Guanqing Liang

Interpretation methods to reveal the internal reasoning processes behind machine learning models have attracted increasing attention in recent years. To quantify the extent to which the identified interpretations truly r…

Decision Making

SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models

2026-02-08 · Weijiang Lv, Yaoxuan Feng, Xiaobo Xia, Jiayu Wang 외 arxiv

Chain-of-Thought reasoning is widely used to improve the interpretability of multimodal large language models (MLLMs), yet the faithfulness of the generated reasoning traces remains unclear. Prior work has mainly focused…