{"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/music-understanding-llama-advancing-text-to","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","arxiv_id":"2308.11276","date":"2023-08-22","proceeding":null,"authors":["Shansong Liu","Atin Sakkeer Hussain","Chenshuo Sun","Ying Shan"],"abstract":"Text-to-music generation (T2M-Gen) faces a major obstacle due to the scarcity of large-scale publicly available music datasets with natural language captions. To address this, we propose the Music Understanding LLaMA (MU-LLaMA), capable of answering music-related questions and generating captions for music files. Our model utilizes audio representations from a pretrained MERT model to extract music features. However, obtaining a suitable dataset for training the MU-LLaMA model remains challenging, as existing publicly accessible audio question answering datasets lack the necessary depth for open-ended music question answering. To fill this gap, we present a methodology for generating question-answer pairs from existing audio captioning datasets and introduce the MusicQA Dataset designed for answering open-ended music-related questions. The experiments demonstrate that the proposed MU-LLaMA model, trained on our designed MusicQA dataset, achieves outstanding performance in both music question answering and music caption generation across various metrics, outperforming current state-of-the-art (SOTA) models in both fields and offering a promising advancement in the T2M-Gen research field.","url_abs":"https://arxiv.org/abs/2308.11276v1","url_pdf":"https://arxiv.org/pdf/2308.11276v1.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":"music-understanding-llama-advancing-text-to","repo_url":"https://github.com/crypto-code/mu-llama","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"music-understanding-llama-advancing-text-to","repo_url":"https://github.com/shansongliu/M2UGen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"music-understanding-llama-advancing-text-to","repo_url":"https://github.com/shansongliu/MU-LLaMA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multimodal-music-generation","task_name":"Multimodal Music Generation"},{"task_slug":"music-captioning","task_name":"Music Captioning"},{"task_slug":"music-question-answering","task_name":"Music Question Answering"},{"task_slug":"text-to-music-generation","task_name":"Text-to-Music Generation"}],"methods":[],"datasets_introduced":[{"slug":"musicqa","name":"MusicQA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/music-question-answering-on-musicqa","task":"Music Question Answering","dataset":"MusicQA","model":"MU-LLaMA","rank_in_archive_order":1,"of":3,"metrics":{"BERT Score":"0.901","BLEU":"0.306","METEOR":"0.385","ROUGE":"0.466"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.11276","atlas_url":"https://app.syntology.ai/?focus=2308.11276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11276"}},"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/shansongliu/M2UGen","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/crypto-code/mu-llama","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shansongliu/MU-LLaMA","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran_fixture":2,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"b47d48e431b34acd","entry":"apply_rotary_emb","repo":"crypto-code/mu-llama","repo_kind":"official","path":"MU-LLaMA/llama/llama.py","file_url":"https://github.com/crypto-code/mu-llama/blob/HEAD/MU-LLaMA/llama/llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b47d48e431b34acd"}},{"code_sha256_prefix":"14a84c2cbfebc413","entry":"precompute_freqs_cis","repo":"crypto-code/mu-llama","repo_kind":"official","path":"MU-LLaMA/llama/llama.py","file_url":"https://github.com/crypto-code/mu-llama/blob/HEAD/MU-LLaMA/llama/llama.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"code_sha256_prefix":"70bf6ebaafd266c4","entry":"reshape_for_broadcast","repo":"crypto-code/mu-llama","repo_kind":"official","path":"MU-LLaMA/llama/llama.py","file_url":"https://github.com/crypto-code/mu-llama/blob/HEAD/MU-LLaMA/llama/llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"70bf6ebaafd266c4"}},{"code_sha256_prefix":"fc374848fd574449","entry":"split_audio","repo":"crypto-code/mu-llama","repo_kind":"official","path":"ModelEvaluations/generate_llama-adapter.py","file_url":"https://github.com/crypto-code/mu-llama/blob/HEAD/ModelEvaluations/generate_llama-adapter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"fc374848fd574449"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}