{"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/lloco-learning-long-contexts-offline","title":"LLoCO: Learning Long Contexts Offline","arxiv_id":"2404.07979","date":"2024-04-11","proceeding":null,"authors":["Sijun Tan","Xiuyu Li","Shishir Patil","Ziyang Wu","Tianjun Zhang","Kurt Keutzer","Joseph E. Gonzalez","Raluca Ada Popa"],"abstract":"Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose LLoCO, a novel approach to address this problem by learning contexts offline through context compression and in-domain parameter-efficient finetuning with LoRA. Our method enables an LLM to create a concise representation of the original context and efficiently retrieve relevant information to answer questions accurately. Our approach extends the effective context window of a 4k token LLaMA2-7B model to handle up to 128k tokens. We evaluate our approach on several long-context question-answering datasets, demonstrating that LLoCO significantly outperforms in-context learning while using $30\\times$ fewer tokens during inference. LLoCO achieves up to $7.62\\times$ speed-up during inference and $11.52\\times$ higher throughput during finetuning, substantially reduces the cost of long document question answering. This makes it a promising solution for efficient long context processing. Our code is publicly available on https://github.com/jeffreysijuntan/lloco.","url_abs":"https://arxiv.org/abs/2404.07979v2","url_pdf":"https://arxiv.org/pdf/2404.07979v2.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":"lloco-learning-long-contexts-offline","repo_url":"https://github.com/jeffreysijuntan/lloco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"4k","task_name":"4k"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2404.07979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07979"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jeffreysijuntan/lloco","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"8cce01de15fdc4a1","entry":"CausalACOutputWithPast","repo":"jeffreysijuntan/lloco","repo_kind":"official","path":"auto_compressor.py","file_url":"https://github.com/jeffreysijuntan/lloco/blob/HEAD/auto_compressor.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":"8cce01de15fdc4a1"}},{"code_sha256_prefix":"4c0a7a2269e32d18","entry":"SummaryConfig","repo":"jeffreysijuntan/lloco","repo_kind":"official","path":"auto_compressor.py","file_url":"https://github.com/jeffreysijuntan/lloco/blob/HEAD/auto_compressor.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":"4c0a7a2269e32d18"}},{"code_sha256_prefix":"5f03a86c025b034c","entry":"LLoCOAutoCompressorMixin","repo":"jeffreysijuntan/lloco","repo_kind":"official","path":"auto_compressor.py","file_url":"https://github.com/jeffreysijuntan/lloco/blob/HEAD/auto_compressor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f03a86c025b034c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}