{"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/cost-effective-hyperparameter-optimization","title":"Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference","arxiv_id":"2303.04673","date":"2023-03-08","proceeding":null,"authors":["Chi Wang","Susan Xueqing Liu","Ahmed H. Awadallah"],"abstract":"Large Language Models (LLMs) have sparked significant interest in their generative capabilities, leading to the development of various commercial applications. The high cost of using the models drives application builders to maximize the value of generation under a limited inference budget. This paper presents a study of optimizing inference hyperparameters such as the number of responses, temperature and max tokens, which significantly affects the utility/cost of text generation. We design a framework named EcoOptiGen which leverages economical hyperparameter optimization and cost-based pruning. Experiments with the GPT-3.5/GPT-4 models on a variety of tasks verify its effectiveness. EcoOptiGen is implemented in the `autogen' package of the FLAML library: \\url{https://aka.ms/autogen}.","url_abs":"https://arxiv.org/abs/2303.04673v2","url_pdf":"https://arxiv.org/pdf/2303.04673v2.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":"cost-effective-hyperparameter-optimization","repo_url":"https://github.com/microsoft/FLAML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"cost-effective-hyperparameter-optimization","repo_url":"https://github.com/kevin666aa/flaml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"cost-effective-hyperparameter-optimization","repo_url":"https://github.com/qingyun-wu/autogen-eval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"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"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04673"}},"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/microsoft/FLAML","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kevin666aa/flaml","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qingyun-wu/autogen-eval","reach":null}],"summary":{"ran":1,"ran_honours":1,"unverified":7},"by_repo_kind":{"listed":{"samples":9,"ran":2,"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":9,"samples":[{"code_sha256_prefix":"735fc5841569ed55","entry":"last_boxed_only_string","repo":"kevin666aa/flaml","repo_kind":"listed","path":"flaml/autogen/math_utils.py","file_url":"https://github.com/kevin666aa/flaml/blob/HEAD/flaml/autogen/math_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"735fc5841569ed55"}},{"code_sha256_prefix":"f29ed149e7409855","entry":"size","repo":"kevin666aa/flaml","repo_kind":"listed","path":"flaml/automl/automl.py","file_url":"https://github.com/kevin666aa/flaml/blob/HEAD/flaml/automl/automl.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f29ed149e7409855"}},{"code_sha256_prefix":"9e35166f7ff26642","entry":"construct_portfolio","repo":"kevin666aa/flaml","repo_kind":"listed","path":"flaml/default/greedy.py","file_url":"https://github.com/kevin666aa/flaml/blob/HEAD/flaml/default/greedy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"9e35166f7ff26642"}},{"code_sha256_prefix":"0a954340369b7456","entry":"extract_code","repo":"kevin666aa/flaml","repo_kind":"listed","path":"flaml/autogen/code_utils.py","file_url":"https://github.com/kevin666aa/flaml/blob/HEAD/flaml/autogen/code_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"0a954340369b7456"}},{"code_sha256_prefix":"e39afdb161a4801c","entry":"infer_lang","repo":"kevin666aa/flaml","repo_kind":"listed","path":"flaml/autogen/code_utils.py","file_url":"https://github.com/kevin666aa/flaml/blob/HEAD/flaml/autogen/code_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e39afdb161a4801c"}},{"code_sha256_prefix":"b25f8ddaf50f92e4","entry":"is_in_sklearn_metric_name_set","repo":"kevin666aa/flaml","repo_kind":"listed","path":"flaml/automl/ml.py","file_url":"https://github.com/kevin666aa/flaml/blob/HEAD/flaml/automl/ml.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b25f8ddaf50f92e4"}},{"code_sha256_prefix":"c99229a5ec259479","entry":"load_openml_dataset","repo":"kevin666aa/flaml","repo_kind":"listed","path":"flaml/automl/data.py","file_url":"https://github.com/kevin666aa/flaml/blob/HEAD/flaml/automl/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c99229a5ec259479"}},{"code_sha256_prefix":"a19f7de8ef80a737","entry":"load_openml_task","repo":"kevin666aa/flaml","repo_kind":"listed","path":"flaml/automl/data.py","file_url":"https://github.com/kevin666aa/flaml/blob/HEAD/flaml/automl/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a19f7de8ef80a737"}},{"code_sha256_prefix":"33b20bbce665cc7a","entry":"remove_boxed","repo":"kevin666aa/flaml","repo_kind":"listed","path":"flaml/autogen/math_utils.py","file_url":"https://github.com/kevin666aa/flaml/blob/HEAD/flaml/autogen/math_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"33b20bbce665cc7a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}