{"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/bento-benchmark-task-reduction-with-in","title":"BenTo: Benchmark Task Reduction with In-Context Transferability","arxiv_id":"2410.13804","date":"2024-10-17","proceeding":null,"authors":["Hongyu Zhao","Ming Li","Lichao Sun","Tianyi Zhou"],"abstract":"Evaluating large language models (LLMs) is costly: it requires the generation and examination of LLM outputs on a large-scale benchmark of various tasks. This paper investigates how to efficiently reduce the tasks used to benchmark LLMs without affecting the evaluation quality. Our study reveals that task transferability and relevance provide critical information to identify the most representative subset of tasks via optimizing a facility location function. We propose a practically efficient metric for estimating the transferability between two tasks via in-context learning (ICL). By analyzing the pairwise transferability, we can reduce tasks in a modern LLM benchmark (e.g., MMLU or FLAN) to 5% while inducing only a <4% difference to the evaluation on the original benchmark. Compared to prior works, our method is training-free, gradient-free, and highly efficient requiring ICL only.","url_abs":"https://arxiv.org/abs/2410.13804v3","url_pdf":"https://arxiv.org/pdf/2410.13804v3.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":"bento-benchmark-task-reduction-with-in","repo_url":"https://github.com/tianyi-lab/bento","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"mmlu","task_name":"MMLU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.13804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13804"}},"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/tianyi-lab/bento","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":10,"unverified":3},"by_repo_kind":{"official":{"samples":13,"ran":10,"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":"d342730858d06a73","entry":"batch_infer_multiple_choice","repo":"tianyi-lab/bento","repo_kind":"official","path":"inference.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/inference.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":"d342730858d06a73"}},{"code_sha256_prefix":"baa0ace81c394eb3","entry":"close_cycle","repo":"tianyi-lab/bento","repo_kind":"official","path":"benchmark-reduction/plot.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/benchmark-reduction/plot.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":"baa0ace81c394eb3"}},{"code_sha256_prefix":"6fb31792767879ab","entry":"find_optimal_ordering","repo":"tianyi-lab/bento","repo_kind":"official","path":"benchmark-reduction/analysis.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/benchmark-reduction/analysis.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":"6fb31792767879ab"}},{"code_sha256_prefix":"be70f4753f03171a","entry":"format_example_flan","repo":"tianyi-lab/bento","repo_kind":"official","path":"prompts.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/prompts.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":"be70f4753f03171a"}},{"code_sha256_prefix":"e068953fcd932df6","entry":"format_example_mmlu","repo":"tianyi-lab/bento","repo_kind":"official","path":"prompts.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/prompts.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":"e068953fcd932df6"}},{"code_sha256_prefix":"5cbdf932859e17b8","entry":"gen_prompt_mmlu","repo":"tianyi-lab/bento","repo_kind":"official","path":"prompts.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/prompts.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":"5cbdf932859e17b8"}},{"code_sha256_prefix":"a4439ebb3e6536fd","entry":"load_csv","repo":"tianyi-lab/bento","repo_kind":"official","path":"benchmark-reduction/analysis_compare_methods_.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/benchmark-reduction/analysis_compare_methods_.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":"a4439ebb3e6536fd"}},{"code_sha256_prefix":"1b7a6ef6b06e147c","entry":"load_csv","repo":"tianyi-lab/bento","repo_kind":"official","path":"benchmark-reduction/analysis_compare_methods_flan.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/benchmark-reduction/analysis_compare_methods_flan.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":"1b7a6ef6b06e147c"}},{"code_sha256_prefix":"5caec032cc3549d1","entry":"load_csv","repo":"tianyi-lab/bento","repo_kind":"official","path":"benchmark-reduction/analysis.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/benchmark-reduction/analysis.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":"5caec032cc3549d1"}},{"code_sha256_prefix":"96537f07b172960c","entry":"separate_rows","repo":"tianyi-lab/bento","repo_kind":"official","path":"benchmark-reduction/analysis_compare_methods_.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/benchmark-reduction/analysis_compare_methods_.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":"96537f07b172960c"}},{"code_sha256_prefix":"3bf1c3c00271897f","entry":"batch_split","repo":"tianyi-lab/bento","repo_kind":"official","path":"inference.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/inference.py","link_basis":"harvester_set","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":"3bf1c3c00271897f"}},{"code_sha256_prefix":"e1e528295e3ea8a4","entry":"find_optimal_ordering","repo":"tianyi-lab/bento","repo_kind":"official","path":"benchmark-reduction/analysis_compare_methods_.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/benchmark-reduction/analysis_compare_methods_.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":"e1e528295e3ea8a4"}},{"code_sha256_prefix":"5dc37098fd3e0e07","entry":"prepare_input","repo":"tianyi-lab/bento","repo_kind":"official","path":"inference.py","file_url":"https://github.com/tianyi-lab/bento/blob/HEAD/inference.py","link_basis":"harvester_set","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":"5dc37098fd3e0e07"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}