Measuring Fairness in Large Audio Language Models via Semantic-Aware Bias Estimation

Excerpt

arXiv:2608.13624v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) have seen increasing use for audio understanding tasks such as speech recognition and audio question answering, raising concerns about fairness across demographic subgroups. Fairness evaluation in spoken-input settings is challenging due to confounding factors, including semantic variation in spoken content and speaker-specific characteristics. Ignoring these factors can result in misleading conclusions about m