{"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/black-box-prompt-optimization-aligning-large","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","arxiv_id":"2311.04155","date":"2023-11-07","proceeding":null,"authors":["Jiale Cheng","Xiao Liu","Kehan Zheng","Pei Ke","Hongning Wang","Yuxiao Dong","Jie Tang","Minlie Huang"],"abstract":"Large language models (LLMs) have shown impressive success in various applications. However, these models are often not well aligned with human intents, which calls for additional treatments on them; that is, the alignment problem. To make LLMs better follow user instructions, existing alignment methods primarily focus on further training them. However, the extra training of LLMs is usually expensive in terms of GPU computing; even worse, some LLMs are not accessible for user-demanded training, such as GPTs. In this work, we take a different perspective -- Black-Box Prompt Optimization (BPO) -- to perform alignments. The idea is to optimize user prompts to suit LLMs' input understanding, so as to best realize users' intents without updating LLMs' parameters. BPO leverages human preferences to optimize prompts, thus making it superior to LLM (e.g., ChatGPT) as a prompt engineer. Moreover, BPO is model-agnostic, and the empirical results demonstrate that the BPO-aligned ChatGPT yields a 22% increase in the win rate against its original version and 10% for GPT-4. Notably, the BPO-aligned LLMs can outperform the same models aligned by PPO and DPO, and it also brings additional performance gains when combining BPO with PPO or DPO. Code and datasets are released at https://github.com/thu-coai/BPO.","url_abs":"https://arxiv.org/abs/2311.04155v3","url_pdf":"https://arxiv.org/pdf/2311.04155v3.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":"black-box-prompt-optimization-aligning-large","repo_url":"https://github.com/thu-coai/bpo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"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":"dpo","method_name":"DPO"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"focus","method_name":"Focus"},{"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":"ppo","method_name":"PPO"},{"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=2311.04155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04155"}},"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/thu-coai/bpo","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"53444f4af7b67958","entry":"build_template_default","repo":"thu-coai/bpo","repo_kind":"official","path":"src/training/data_processer.py","file_url":"https://github.com/thu-coai/bpo/blob/HEAD/src/training/data_processer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53444f4af7b67958"}},{"code_sha256_prefix":"12f81c87374a4ab2","entry":"build_template_llama","repo":"thu-coai/bpo","repo_kind":"official","path":"src/training/data_processer.py","file_url":"https://github.com/thu-coai/bpo/blob/HEAD/src/training/data_processer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12f81c87374a4ab2"}},{"code_sha256_prefix":"b8b3a308395df443","entry":"build_template_tiger","repo":"thu-coai/bpo","repo_kind":"official","path":"src/training/data_processer.py","file_url":"https://github.com/thu-coai/bpo/blob/HEAD/src/training/data_processer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b8b3a308395df443"}},{"code_sha256_prefix":"b629ae49b12e3de3","entry":"postprocess","repo":"thu-coai/bpo","repo_kind":"official","path":"src/training/data_utils.py","file_url":"https://github.com/thu-coai/bpo/blob/HEAD/src/training/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b629ae49b12e3de3"}},{"code_sha256_prefix":"ce3e76d93e76d129","entry":"preprocess","repo":"thu-coai/bpo","repo_kind":"official","path":"src/training/data_utils.py","file_url":"https://github.com/thu-coai/bpo/blob/HEAD/src/training/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ce3e76d93e76d129"}},{"code_sha256_prefix":"c6e5695547deaf80","entry":"chat_gpt","repo":"thu-coai/bpo","repo_kind":"official","path":"src/data_construction/chatgpt_infer.py","file_url":"https://github.com/thu-coai/bpo/blob/HEAD/src/data_construction/chatgpt_infer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6e5695547deaf80"}},{"code_sha256_prefix":"1350e6afade56462","entry":"chat_gpt","repo":"thu-coai/bpo","repo_kind":"official","path":"src/evaluation/gpt4_score.py","file_url":"https://github.com/thu-coai/bpo/blob/HEAD/src/evaluation/gpt4_score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1350e6afade56462"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}