{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/can-large-audio-language-models-truly-hear","title":"Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning","arxiv_id":"2410.16130","date":"2024-10-21","proceeding":null,"authors":["Chun-Yi Kuan","Hung-Yi Lee"],"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.","url_abs":"https://arxiv.org/abs/2410.16130v2","url_pdf":"https://arxiv.org/pdf/2410.16130v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"can-large-audio-language-models-truly-hear","repo_url":"https://github.com/kuan2jiu99/audio-hallucination","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.16130","atlas_url":"https://app.syntology.ai/?focus=2410.16130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16130"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kuan2jiu99/audio-hallucination","reach":{"status":"ok"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"fb60c91084920422","entry":"cal_CHAIRscore","repo":"kuan2jiu99/audio-hallucination","repo_kind":"official","path":"interspeech2024/generative_tasks/evaluation.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/interspeech2024/generative_tasks/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb60c91084920422"}},{"code_sha256_prefix":"60cdccbd6a5dbd07","entry":"cal_Cover_score","repo":"kuan2jiu99/audio-hallucination","repo_kind":"official","path":"interspeech2024/generative_tasks/evaluation.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/interspeech2024/generative_tasks/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"60cdccbd6a5dbd07"}},{"code_sha256_prefix":"b1c856ce62873154","entry":"check_answer","repo":"kuan2jiu99/audio-hallucination","repo_kind":"official","path":"icassp2025/evaluation.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/icassp2025/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1c856ce62873154"}},{"code_sha256_prefix":"ccc0c3e69385b7eb","entry":"evaluation","repo":"kuan2jiu99/audio-hallucination","repo_kind":"official","path":"icassp2025/evaluation.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/icassp2025/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ccc0c3e69385b7eb"}},{"code_sha256_prefix":"8d1a616242359eee","entry":"evaluation","repo":"kuan2jiu99/audio-hallucination","repo_kind":"official","path":"interspeech2024/evaluation.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/interspeech2024/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d1a616242359eee"}},{"code_sha256_prefix":"7d76474f7caf820b","entry":"inference","repo":"kuan2jiu99/audio-hallucination","repo_kind":"official","path":"icassp2025/inference.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/icassp2025/inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d76474f7caf820b"}},{"code_sha256_prefix":"09c061845768f010","entry":"load_json","repo":"kuan2jiu99/audio-hallucination","repo_kind":"official","path":"interspeech2024/generative_tasks/evaluation.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/interspeech2024/generative_tasks/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"09c061845768f010"}},{"code_sha256_prefix":"698b1eaa3d1639e4","entry":"parse_response","repo":"kuan2jiu99/audio-hallucination","repo_kind":"official","path":"icassp2025/evaluation.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/icassp2025/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"698b1eaa3d1639e4"}},{"code_sha256_prefix":"94016dbb5d97a3d5","entry":"parse_response","repo":"kuan2jiu99/audio-hallucination","repo_kind":"official","path":"interspeech2024/evaluation.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/interspeech2024/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94016dbb5d97a3d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}