{"paper":{"title":"LLaSM: Large Language and Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Daochen Shi, Guangyao Chen, Qiqi Xiang, Ruihua Zhang, Siwei Dong, Wenhao Huang, Yemin Shi, Yu Shu","submitted_at":"2023-08-30T10:12:39Z","abstract_excerpt":"Multi-modal large language models have garnered significant interest recently. Though, most of the works focus on vision-language multi-modal models providing strong capabilities in following vision-and-language instructions. However, we claim that speech is also an important modality through which humans interact with the world. Hence, it is crucial for a general-purpose assistant to be able to follow multi-modal speech-and-language instructions. In this work, we propose Large Language and Speech Model (LLaSM). LLaSM is an end-to-end trained large multi-modal speech-language model with cross-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15930","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.15930/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}