{"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/large-language-models-can-self-improve-in","title":"Large Language Models Can Self-Improve in Long-context Reasoning","arxiv_id":"2411.08147","date":"2024-11-12","proceeding":null,"authors":["Siheng Li","Cheng Yang","Zesen Cheng","Lemao Liu","Mo Yu","Yujiu Yang","Wai Lam"],"abstract":"Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fine-tuning LLMs with synthetic data, which depends on annotations from human experts or advanced models like GPT-4, thus restricting further advancements. To address this issue, we investigate the potential for LLMs to self-improve in long-context reasoning and propose \\ours, an approach specifically designed for this purpose. This approach is straightforward: we sample multiple outputs for each question, score them with Minimum Bayes Risk, and then apply supervised fine-tuning or preference optimization based on these outputs. Extensive experiments on several leading LLMs demonstrate the effectiveness of \\ours, with an absolute improvement of $4.2$ points for Llama-3.1-8B-Instruct. Furthermore, \\ours achieves superior performance compared to prior approaches that depend on data produced by human experts or advanced models. We anticipate that this work will open new avenues for self-improvement techniques in long-context scenarios, which are essential for the continual advancement of LLMs.","url_abs":"https://arxiv.org/abs/2411.08147v1","url_pdf":"https://arxiv.org/pdf/2411.08147v1.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":"large-language-models-can-self-improve-in","repo_url":"https://github.com/sihengli99/sealong","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.08147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.08147"}},"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/sihengli99/sealong","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"ran":1,"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":6,"samples":[{"code_sha256_prefix":"dae7ab386661a4f4","entry":"normalize_answer","repo":"sihengli99/sealong","repo_kind":"official","path":"eval_longbench_qa.py","file_url":"https://github.com/sihengli99/sealong/blob/HEAD/eval_longbench_qa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dae7ab386661a4f4"}},{"code_sha256_prefix":"60b60f6b39648abe","entry":"extract_title","repo":"sihengli99/sealong","repo_kind":"official","path":"process_data.py","file_url":"https://github.com/sihengli99/sealong/blob/HEAD/process_data.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":"60b60f6b39648abe"}},{"code_sha256_prefix":"c9ca58e429a785be","entry":"hf_trl_dpo_dataset_map_fn","repo":"sihengli99/sealong","repo_kind":"official","path":"configs/xtuner_orpo.py","file_url":"https://github.com/sihengli99/sealong/blob/HEAD/configs/xtuner_orpo.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":"c9ca58e429a785be"}},{"code_sha256_prefix":"57d86d780856fca7","entry":"hf_trl_sft_dataset_map_fn","repo":"sihengli99/sealong","repo_kind":"official","path":"configs/xtuner_sft.py","file_url":"https://github.com/sihengli99/sealong/blob/HEAD/configs/xtuner_sft.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":"57d86d780856fca7"}},{"code_sha256_prefix":"3a1b300cb40b8be4","entry":"normalize_string","repo":"sihengli99/sealong","repo_kind":"official","path":"process_data.py","file_url":"https://github.com/sihengli99/sealong/blob/HEAD/process_data.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":"3a1b300cb40b8be4"}},{"code_sha256_prefix":"bdc3d946a1bd95c1","entry":"process_item","repo":"sihengli99/sealong","repo_kind":"official","path":"process_data.py","file_url":"https://github.com/sihengli99/sealong/blob/HEAD/process_data.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":"bdc3d946a1bd95c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}