Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models
This addresses reliability issues in LALMs for audio-related tasks, but it is incremental as it focuses on assessing and mitigating a specific weakness rather than introducing a new paradigm.
The study tackled the problem of object hallucination in large audio-language models (LALMs), finding that while they match specialized models in audio understanding, they struggle with discriminative questions about object sounds, with prompt engineering showing potential to improve performance.
Large audio-language models (LALMs) enhance traditional large language models by integrating audio perception capabilities, allowing them to tackle audio-related tasks. Previous research has primarily focused on assessing the performance of LALMs across various tasks, yet overlooking their reliability, particularly concerning issues like object hallucination. In our study, we introduce methods to assess the extent of object hallucination of publicly available LALMs. Our findings reveal that LALMs are comparable to specialized audio captioning models in their understanding of audio content, but struggle to answer discriminative questions, specifically those requiring the identification of the presence of particular object sounds within an audio clip. This limitation highlights a critical weakness in current LALMs: their inadequate understanding of discriminative queries. Moreover, we explore the potential of prompt engineering to enhance LALMs' performance on discriminative questions.