SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.16130 · 2024

Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
kuan2jiu99/audio-hallucination canonical 0 of 9
FunctionStatusWhere it lives
cal_CHAIRscore Not yet run kuan2jiu99/audio-hallucination/interspeech2024/generative_tasks/evaluation.py
pointer only (licence: NONE) · get_code("fb60c91084920422")
cal_Cover_score Not yet run kuan2jiu99/audio-hallucination/interspeech2024/generative_tasks/evaluation.py
pointer only (licence: NONE) · get_code("60cdccbd6a5dbd07")
check_answer Not yet run kuan2jiu99/audio-hallucination/icassp2025/evaluation.py
pointer only (licence: NONE) · get_code("b1c856ce62873154")
evaluation Not yet run kuan2jiu99/audio-hallucination/icassp2025/evaluation.py
pointer only (licence: NONE) · get_code("ccc0c3e69385b7eb")
evaluation Not yet run kuan2jiu99/audio-hallucination/interspeech2024/evaluation.py
pointer only (licence: NONE) · get_code("8d1a616242359eee")
inference Not yet run kuan2jiu99/audio-hallucination/icassp2025/inference.py
pointer only (licence: NONE) · get_code("7d76474f7caf820b")
load_json Not yet run kuan2jiu99/audio-hallucination/interspeech2024/generative_tasks/evaluation.py
pointer only (licence: NONE) · get_code("09c061845768f010")
parse_response Not yet run kuan2jiu99/audio-hallucination/icassp2025/evaluation.py
pointer only (licence: NONE) · get_code("698b1eaa3d1639e4")
parse_response Not yet run kuan2jiu99/audio-hallucination/interspeech2024/evaluation.py
pointer only (licence: NONE) · get_code("94016dbb5d97a3d5")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent advancements in large audio-language models (LALMs) have shown impressive capabilities in understanding and reasoning about audio and speech information. However, these models still face challenges, including hallucinating non-existent sound events, misidentifying the order of sound events, and incorrectly attributing sound sources, which undermine their reliability and real-world application. To systematically evaluate these issues, we propose three distinct tasks: object existence, temporal order, and object attribute within audio. These tasks assess the models' comprehension of critical audio information aspects. Our experimental results reveal limitations in these fundamental tasks, underscoring the need for better models in recognizing specific sound events, determining event sequences, and identifying sound sources. To improve performance in these areas, we introduce a multi-turn chain-of-thought approach, which demonstrates significantly improved model performance across the proposed tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.16130")
get_code_for_paper("2410.16130")
have("2410.16130")

Connect an agent — have() is free.