{"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/sakura-on-the-multi-hop-reasoning-of-large","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","arxiv_id":"2505.13237","date":"2025-05-19","proceeding":null,"authors":["Chih-Kai Yang","Neo Ho","Yen-Ting Piao","Hung-Yi Lee"],"abstract":"Large audio-language models (LALMs) extend the large language models with multimodal understanding in speech, audio, etc. While their performances on speech and audio-processing tasks are extensively studied, their reasoning abilities remain underexplored. Particularly, their multi-hop reasoning, the ability to recall and integrate multiple facts, lacks systematic evaluation. Existing benchmarks focus on general speech and audio-processing tasks, conversational abilities, and fairness but overlook this aspect. To bridge this gap, we introduce SAKURA, a benchmark assessing LALMs' multi-hop reasoning based on speech and audio information. Results show that LALMs struggle to integrate speech/audio representations for multi-hop reasoning, even when they extract the relevant information correctly, highlighting a fundamental challenge in multimodal reasoning. Our findings expose a critical limitation in LALMs, offering insights and resources for future research.","url_abs":"https://arxiv.org/abs/2505.13237v2","url_pdf":"https://arxiv.org/pdf/2505.13237v2.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":"sakura-on-the-multi-hop-reasoning-of-large","repo_url":"https://github.com/b08202033/SAKURA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"sakura-on-the-multi-hop-reasoning-of-large","repo_url":"https://github.com/ckyang1124/sakura","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.13237","atlas_url":"https://app.syntology.ai/?focus=2505.13237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13237"}},"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/ckyang1124/sakura","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/b08202033/SAKURA","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"99c0f4e50a906542","entry":"extract_judgement","repo":"ckyang1124/sakura","repo_kind":"official","path":"evaluation/llm_judge.py","file_url":"https://github.com/ckyang1124/sakura/blob/HEAD/evaluation/llm_judge.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"99c0f4e50a906542"}},{"code_sha256_prefix":"4c6c9926d43d2ecf","entry":"query_llm","repo":"ckyang1124/sakura","repo_kind":"official","path":"evaluation/llm_judge.py","file_url":"https://github.com/ckyang1124/sakura/blob/HEAD/evaluation/llm_judge.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4c6c9926d43d2ecf"}},{"code_sha256_prefix":"5a7528f5f02fdae8","entry":"read_json_file","repo":"ckyang1124/sakura","repo_kind":"official","path":"evaluation/llm_judge.py","file_url":"https://github.com/ckyang1124/sakura/blob/HEAD/evaluation/llm_judge.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a7528f5f02fdae8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}