{"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/direct-large-language-model-alignment-through","title":"Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation","arxiv_id":"2402.11907","date":"2024-02-19","proceeding":null,"authors":["Aiwei Liu","Haoping Bai","Zhiyun Lu","Xiang Kong","Simon Wang","Jiulong Shan","Meng Cao","Lijie Wen"],"abstract":"Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the response preference by using the output probabilities of response pairs under contrastive prompt pairs, which could achieve better performance on LLaMA2-7B and LLaMA2-13B compared to RLAIF. Based on this, we propose an automatic alignment method, Direct Large Model Alignment (DLMA). First, we use contrastive prompt pairs to automatically generate preference data. Then, we continue to evaluate the generated preference data using contrastive prompt pairs and calculate a self-rewarding score. Finally, we use the DPO algorithm to effectively align LLMs by combining this self-rewarding score. In the experimental stage, our DLMA method could surpass the \\texttt{RLHF} method without relying on human-annotated preference data.","url_abs":"https://arxiv.org/abs/2402.11907v2","url_pdf":"https://arxiv.org/pdf/2402.11907v2.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":"direct-large-language-model-alignment-through","repo_url":"https://github.com/exlaw/dlma","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"dpo","method_name":"DPO"},{"method_slug":"rlaif","method_name":"RLAIF"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.11907","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11907"}},"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/exlaw/dlma","reach":null}],"summary":{"ran_fixture":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":0,"samples":[{"code_sha256_prefix":"838a07604a66c6c3","entry":"preference_loss","repo":"exlaw/dlma","repo_kind":"official","path":"trainers.py","file_url":"https://github.com/exlaw/dlma/blob/HEAD/trainers.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"838a07604a66c6c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}