Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913388520538112 |
|---|---|
| author | Kuan, Chun-Yi Huang, Wei-Ping Lee, Hung-yi |
| author_facet | Kuan, Chun-Yi Huang, Wei-Ping Lee, Hung-yi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08402 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models Kuan, Chun-Yi Huang, Wei-Ping Lee, Hung-yi Audio and Speech Processing Computation and Language Machine Learning Sound 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. |
| title | Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models |
| topic | Audio and Speech Processing Computation and Language Machine Learning Sound |
| url | https://arxiv.org/abs/2406.08402 |