{"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/longreward-improving-long-context-large","title":"LongReward: Improving Long-context Large Language Models with AI Feedback","arxiv_id":"2410.21252","date":"2024-10-28","proceeding":null,"authors":["Jiajie Zhang","Zhongni Hou","Xin Lv","Shulin Cao","Zhenyu Hou","Yilin Niu","Lei Hou","Yuxiao Dong","Ling Feng","Juanzi Li"],"abstract":"Though significant advancements have been achieved in developing long-context large language models (LLMs), the compromised quality of LLM-synthesized data for supervised fine-tuning (SFT) often affects the long-context performance of SFT models and leads to inherent limitations. In principle, reinforcement learning (RL) with appropriate reward signals can further enhance models' capacities. However, how to obtain reliable rewards in long-context scenarios remains unexplored. To this end, we propose LongReward, a novel method that utilizes an off-the-shelf LLM to provide rewards for long-context model responses from four human-valued dimensions: helpfulness, logicality, faithfulness, and completeness, each with a carefully designed assessment pipeline. By combining LongReward and offline RL algorithm DPO, we are able to effectively improve long-context SFT models. Our experiments indicate that LongReward not only significantly improves models' long-context performance but also enhances their ability to follow short instructions. We also find that long-context DPO with LongReward and conventional short-context DPO can be used together without hurting either one's performance.","url_abs":"https://arxiv.org/abs/2410.21252v1","url_pdf":"https://arxiv.org/pdf/2410.21252v1.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":"longreward-improving-long-context-large","repo_url":"https://github.com/THUDM/LongReward","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"dpo","method_name":"DPO"},{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.21252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21252"}},"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/THUDM/LongReward","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"0bfaa3f127f9fbd7","entry":"find_last_number","repo":"THUDM/LongReward","repo_kind":"official","path":"long_reward/auto_scorer.py","file_url":"https://github.com/THUDM/LongReward/blob/HEAD/long_reward/auto_scorer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0bfaa3f127f9fbd7"}},{"code_sha256_prefix":"6b78ba017291e130","entry":"get_lang","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6b78ba017291e130"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}