{"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/bbox-adapter-lightweight-adapting-for-black","title":"BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models","arxiv_id":"2402.08219","date":"2024-02-13","proceeding":null,"authors":["Haotian Sun","Yuchen Zhuang","Wei Wei","Chao Zhang","Bo Dai"],"abstract":"Adapting state-of-the-art Large Language Models (LLMs) like GPT-4 and Gemini for specific tasks is challenging. Due to the opacity in their parameters, embeddings, and even output probabilities, existing fine-tuning adaptation methods are inapplicable. Consequently, adapting these black-box LLMs is only possible through their API services, raising concerns about transparency, privacy, and cost. To address these challenges, we introduce BBox-Adapter, a novel lightweight adapter for black-box LLMs. BBox-Adapter distinguishes target and source domain data by treating target data as positive and source data as negative. It employs a ranking-based Noise Contrastive Estimation (NCE) loss to promote the likelihood of target domain data while penalizing that of the source domain. Furthermore, it features an online adaptation mechanism, which incorporates real-time positive data sampling from ground-truth, human, or AI feedback, coupled with negative data from previous adaptations. Extensive experiments demonstrate BBox-Adapter's effectiveness and cost efficiency. It improves model performance by up to 6.77% across diverse tasks and domains, while reducing training and inference costs by 31.30x and 1.84x, respectively.","url_abs":"https://arxiv.org/abs/2402.08219v2","url_pdf":"https://arxiv.org/pdf/2402.08219v2.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":"bbox-adapter-lightweight-adapting-for-black","repo_url":"https://github.com/haotiansun14/bbox-adapter","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":"adapter","method_name":"Adapter"},{"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=2402.08219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08219"}},"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/haotiansun14/bbox-adapter","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"6731183eb0c6819d","entry":"extract_answer","repo":"haotiansun14/bbox-adapter","repo_kind":"official","path":"utils/gsm8k_metric.py","file_url":"https://github.com/haotiansun14/bbox-adapter/blob/HEAD/utils/gsm8k_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6731183eb0c6819d"}},{"code_sha256_prefix":"eb4554f77207ac70","entry":"extract_number","repo":"haotiansun14/bbox-adapter","repo_kind":"official","path":"utils/scienceqa_metric.py","file_url":"https://github.com/haotiansun14/bbox-adapter/blob/HEAD/utils/scienceqa_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb4554f77207ac70"}},{"code_sha256_prefix":"5e1cdcbfba6b4853","entry":"is_correct","repo":"haotiansun14/bbox-adapter","repo_kind":"official","path":"utils/gsm8k_metric.py","file_url":"https://github.com/haotiansun14/bbox-adapter/blob/HEAD/utils/gsm8k_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5e1cdcbfba6b4853"}},{"code_sha256_prefix":"1ab7fd2652fb1b93","entry":"is_correct","repo":"haotiansun14/bbox-adapter","repo_kind":"official","path":"utils/scienceqa_metric.py","file_url":"https://github.com/haotiansun14/bbox-adapter/blob/HEAD/utils/scienceqa_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1ab7fd2652fb1b93"}},{"code_sha256_prefix":"e7d71a1601731b99","entry":"parse_last_number","repo":"haotiansun14/bbox-adapter","repo_kind":"official","path":"utils/gsm8k_metric.py","file_url":"https://github.com/haotiansun14/bbox-adapter/blob/HEAD/utils/gsm8k_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e7d71a1601731b99"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}