{"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/llark-a-multimodal-foundation-model-for-music","title":"LLark: A Multimodal Instruction-Following Language Model for Music","arxiv_id":"2310.07160","date":"2023-10-11","proceeding":null,"authors":["Josh Gardner","Simon Durand","Daniel Stoller","Rachel M. Bittner"],"abstract":"Music has a unique and complex structure which is challenging for both expert humans and existing AI systems to understand, and presents unique challenges relative to other forms of audio. We present LLark, an instruction-tuned multimodal model for \\emph{music} understanding. We detail our process for dataset creation, which involves augmenting the annotations of diverse open-source music datasets and converting them to a unified instruction-tuning format. We propose a multimodal architecture for LLark, integrating a pretrained generative model for music with a pretrained language model. In evaluations on three types of tasks (music understanding, captioning, reasoning), we show that LLark matches or outperforms existing baselines in music understanding, and that humans show a high degree of agreement with its responses in captioning and reasoning tasks. LLark is trained entirely from open-source music data and models, and we make our training code available along with the release of this paper. Additional results and audio examples are at https://bit.ly/llark, and our source code is available at https://github.com/spotify-research/llark .","url_abs":"https://arxiv.org/abs/2310.07160v3","url_pdf":"https://arxiv.org/pdf/2310.07160v3.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":"llark-a-multimodal-foundation-model-for-music","repo_url":"https://github.com/spotify-research/llark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.07160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07160"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"deterministic:regex_extraction","url":"https://github.com/p-lambda/jukemir","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/mdeff/fma","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/spotify-research/llark","reach":null}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"found_in_text":{"samples":4,"ran":4,"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":"b6b5a8415848391b","entry":"WrappedLlamav2Config","repo":"spotify-research/llark","repo_kind":"official","path":"m2t/models/llamav2.py","file_url":"https://github.com/spotify-research/llark/blob/HEAD/m2t/models/llamav2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b6b5a8415848391b"}},{"code_sha256_prefix":"0121345102f5ff03","entry":"build_sample_loader","repo":"mdeff/fma","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/mdeff/fma/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0121345102f5ff03"}},{"code_sha256_prefix":"46a60ba365931494","entry":"convert_duration","repo":"mdeff/fma","repo_kind":"found_in_text","path":"creation.py","file_url":"https://github.com/mdeff/fma/blob/HEAD/creation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46a60ba365931494"}},{"code_sha256_prefix":"f7bb5dc60935c4cc","entry":"get_audio_path","repo":"mdeff/fma","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/mdeff/fma/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7bb5dc60935c4cc"}},{"code_sha256_prefix":"fd57d10b2a5fea40","entry":"load","repo":"mdeff/fma","repo_kind":"found_in_text","path":"utils.py","file_url":"https://github.com/mdeff/fma/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd57d10b2a5fea40"}},{"code_sha256_prefix":"e0ec5330c4179e94","entry":"AudioEncoderConfig","repo":"spotify-research/llark","repo_kind":"official","path":"m2t/models/llamav2.py","file_url":"https://github.com/spotify-research/llark/blob/HEAD/m2t/models/llamav2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e0ec5330c4179e94"}},{"code_sha256_prefix":"856e84f8c6dbac47","entry":"WrappedLlamav2Model","repo":"spotify-research/llark","repo_kind":"official","path":"m2t/models/llamav2.py","file_url":"https://github.com/spotify-research/llark/blob/HEAD/m2t/models/llamav2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"856e84f8c6dbac47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}