Large Audio Language Models (LALMs) are increasingly applied to audio understanding and multimodal reasoning, yet their ability to locate when events occur remains underexplored. We present the first systematic study of temporal bias in LALMs, revealing a key limitation in their timestamp prediction. For example, when asked "At which second does the lecturer introduce the key formula?", models often predict timestamps that are consistently earlier or later than the ground truth. Through controlled experiments on timestamped datasets, we find that temporal bias (i) is prevalent across datasets and models, (ii) increases with audio length - even accumulating to tens of seconds in extended recordings, and (iii) varies across event types and positions. We quantify this effect with the Temporal Bias Index (TBI), measuring systematic misalignment in predicted event timings, and complement it with a visualization framework. Our findings highlight a fundamental limitation in current LALMs and call for the development of temporally robust architectures.
Yao et al. (2025) studied this question.