{"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/stronger-random-baselines-for-in-context","title":"Stronger Random Baselines for In-Context Learning","arxiv_id":"2404.13020","date":"2024-04-19","proceeding":null,"authors":["Gregory Yauney","David Mimno"],"abstract":"Evaluating the in-context learning classification performance of language models poses challenges due to small dataset sizes, extensive prompt-selection using the validation set, and intentionally difficult tasks that lead to near-random performance. The standard random baseline--the expected accuracy of guessing labels uniformly at random--is stable when the evaluation set is used only once or when the dataset is large. We account for the common practice of validation set reuse and existing small datasets with a stronger random baseline: the expected maximum accuracy across multiple random classifiers. When choosing the best prompt demonstrations across six quantized language models applied to 16 BIG-bench Lite tasks, more than 20% of the few-shot results that exceed the standard baseline do not exceed this stronger random baseline. When held-out test sets are available, this stronger baseline is also a better predictor of held-out performance than the standard baseline, avoiding unnecessary test set evaluations. This maximum random baseline provides an easily calculated drop-in replacement for the standard baseline.","url_abs":"https://arxiv.org/abs/2404.13020v2","url_pdf":"https://arxiv.org/pdf/2404.13020v2.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":"stronger-random-baselines-for-in-context","repo_url":"https://github.com/gyauney/max-random-baseline","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"stronger-random-baselines-for-in-context","repo_url":"https://github.com/gyauney/stronger-random-baselines","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.13020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13020"}},"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/gyauney/stronger-random-baselines","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gyauney/max-random-baseline","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"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":"f16b77ec8e7dbea7","entry":"max_order_statistic_binomial_F","repo":"gyauney/stronger-random-baselines","repo_kind":"official","path":"figure-9.py","file_url":"https://github.com/gyauney/stronger-random-baselines/blob/HEAD/figure-9.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f16b77ec8e7dbea7"}},{"code_sha256_prefix":"122d703eaf972821","entry":"model_to_display","repo":"gyauney/stronger-random-baselines","repo_kind":"official","path":"bigbench-held-out-splits.py","file_url":"https://github.com/gyauney/stronger-random-baselines/blob/HEAD/bigbench-held-out-splits.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"122d703eaf972821"}},{"code_sha256_prefix":"1cb57af44a27dd12","entry":"normalized_score_to_accuracy","repo":"gyauney/stronger-random-baselines","repo_kind":"official","path":"figure-9.py","file_url":"https://github.com/gyauney/stronger-random-baselines/blob/HEAD/figure-9.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1cb57af44a27dd12"}},{"code_sha256_prefix":"15f489376c6da90e","entry":"approximate_max_random_baseline","repo":"gyauney/stronger-random-baselines","repo_kind":"official","path":"approximate_max_random_baseline.py","file_url":"https://github.com/gyauney/stronger-random-baselines/blob/HEAD/approximate_max_random_baseline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15f489376c6da90e"}},{"code_sha256_prefix":"b8d20a870c94039f","entry":"max_order_statistic_binomial_pmf","repo":"gyauney/stronger-random-baselines","repo_kind":"official","path":"approximate_max_random_baseline.py","file_url":"https://github.com/gyauney/stronger-random-baselines/blob/HEAD/approximate_max_random_baseline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8d20a870c94039f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}