{"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/extending-llms-context-window-with-100","title":"Extending LLMs' Context Window with 100 Samples","arxiv_id":"2401.07004","date":"2024-01-13","proceeding":null,"authors":["Yikai Zhang","Junlong Li","PengFei Liu"],"abstract":"Large Language Models (LLMs) are known to have limited extrapolation ability beyond their pre-trained context window, constraining their application in downstream tasks with lengthy inputs. Recent studies have sought to extend LLMs' context window by modifying rotary position embedding (RoPE), a popular position encoding method adopted by well-known LLMs such as LLaMA, PaLM, and GPT-NeoX. However, prior works like Position Interpolation (PI) and YaRN are resource-intensive and lack comparative experiments to assess their applicability. In this work, we identify the inherent need for LLMs' attention entropy (i.e. the information entropy of attention scores) to maintain stability and introduce a novel extension to RoPE which combines adjusting RoPE's base frequency and scaling the attention logits to help LLMs efficiently adapt to a larger context window. We validate the superiority of our method in both fine-tuning performance and robustness across different context window sizes on various context-demanding tasks. Notably, our method extends the context window of LLaMA-2-7B-Chat to 16,384 with only 100 samples and 6 training steps, showcasing extraordinary efficiency. Finally, we also explore how data compositions and training curricula affect context window extension for specific downstream tasks, suggesting fine-tuning LLMs with lengthy conversations as a good starting point. We release our code and SFT data at https://github.com/GAIR-NLP/Entropy-ABF.","url_abs":"https://arxiv.org/abs/2401.07004v1","url_pdf":"https://arxiv.org/pdf/2401.07004v1.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":"extending-llms-context-window-with-100","repo_url":"https://github.com/gair-nlp/entropy-abf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Position"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"gpt-neox","method_name":"GPT-NeoX"},{"method_slug":"palm","method_name":"PaLM"},{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.07004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.07004"}},"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/gair-nlp/entropy-abf","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":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":"bfdb34e1aab7fad0","entry":"apply_rotary_pos_emb_old","repo":"gair-nlp/entropy-abf","repo_kind":"official","path":"patch/EABF.py","file_url":"https://github.com/gair-nlp/entropy-abf/blob/HEAD/patch/EABF.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bfdb34e1aab7fad0"}},{"code_sha256_prefix":"9acb8a1e7646e193","entry":"collect_probability","repo":"gair-nlp/entropy-abf","repo_kind":"official","path":"retrieve_attn.py","file_url":"https://github.com/gair-nlp/entropy-abf/blob/HEAD/retrieve_attn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9acb8a1e7646e193"}},{"code_sha256_prefix":"e03d53ba9d4f9ae5","entry":"rotate_half","repo":"gair-nlp/entropy-abf","repo_kind":"official","path":"patch/EABF.py","file_url":"https://github.com/gair-nlp/entropy-abf/blob/HEAD/patch/EABF.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e03d53ba9d4f9ae5"}},{"code_sha256_prefix":"138998fbab38fb66","entry":"apply_rotary_pos_emb_scale","repo":"gair-nlp/entropy-abf","repo_kind":"official","path":"patch/EABF.py","file_url":"https://github.com/gair-nlp/entropy-abf/blob/HEAD/patch/EABF.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"138998fbab38fb66"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}