{"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/sample-efficient-alignment-for-llms","title":"Sample-Efficient Alignment for LLMs","arxiv_id":"2411.01493","date":"2024-11-03","proceeding":null,"authors":["Zichen Liu","Changyu Chen","Chao Du","Wee Sun Lee","Min Lin"],"abstract":"We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the frame of contextual dueling bandits. This formulation, subsuming recent paradigms such as online RLHF and online DPO, inherently quests for sample-efficient algorithms that incorporate online active exploration. Leveraging insights from bandit theory, we introduce a unified algorithm based on Thompson sampling and highlight its applications in two distinct LLM alignment scenarios. The practical agent that efficiently implements this algorithm, named SEA (Sample-Efficient Alignment), is empirically validated through extensive experiments across three model scales (1B, 2.8B, 6.9B) and three preference learning algorithms (DPO, IPO, SLiC). The results demonstrate that SEA achieves highly sample-efficient alignment with oracle's preferences, outperforming recent active exploration methods for LLMs. Additionally, we release the implementation of SEA together with an efficient codebase designed for online alignment of LLMs, aiming to accelerate future research in this field.","url_abs":"https://arxiv.org/abs/2411.01493v2","url_pdf":"https://arxiv.org/pdf/2411.01493v2.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":"sample-efficient-alignment-for-llms","repo_url":"https://github.com/sail-sg/oat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"thompson-sampling","task_name":"Thompson Sampling"}],"methods":[{"method_slug":"dpo","method_name":"DPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.01493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.01493"}},"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/sail-sg/oat","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"3826c1fe4f1b5fc1","entry":"apply_no_template","repo":"sail-sg/oat","repo_kind":"official","path":"oat/experiment/run_math_rl.py","file_url":"https://github.com/sail-sg/oat/blob/HEAD/oat/experiment/run_math_rl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3826c1fe4f1b5fc1"}},{"code_sha256_prefix":"193cf4896dff6fbb","entry":"apply_qwen_math_template","repo":"sail-sg/oat","repo_kind":"official","path":"oat/experiment/run_math_rl.py","file_url":"https://github.com/sail-sg/oat/blob/HEAD/oat/experiment/run_math_rl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"193cf4896dff6fbb"}},{"code_sha256_prefix":"05a5bcd33fb0b81f","entry":"apply_r1_template","repo":"sail-sg/oat","repo_kind":"official","path":"oat/experiment/run_math_rl.py","file_url":"https://github.com/sail-sg/oat/blob/HEAD/oat/experiment/run_math_rl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"05a5bcd33fb0b81f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}