{"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/state-of-what-art-a-call-for-multi-prompt-llm","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","arxiv_id":"2401.00595","date":"2023-12-31","proceeding":null,"authors":["Moran Mizrahi","Guy Kaplan","Dan Malkin","Rotem Dror","Dafna Shahaf","Gabriel Stanovsky"],"abstract":"Recent advances in large language models (LLMs) have led to the development of various evaluation benchmarks. These benchmarks typically rely on a single instruction template for evaluating all LLMs on a specific task. In this paper, we comprehensively analyze the brittleness of results obtained via single-prompt evaluations across 6.5M instances, involving 20 different LLMs and 39 tasks from 3 benchmarks. To improve robustness of the analysis, we propose to evaluate LLMs with a set of diverse prompts instead. We discuss tailored evaluation metrics for specific use cases (e.g., LLM developers vs. developers interested in a specific downstream task), ensuring a more reliable and meaningful assessment of LLM capabilities. We then implement these criteria and conduct evaluations of multiple models, providing insights into the true strengths and limitations of current LLMs.","url_abs":"https://arxiv.org/abs/2401.00595v3","url_pdf":"https://arxiv.org/pdf/2401.00595v3.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":"state-of-what-art-a-call-for-multi-prompt-llm","repo_url":"https://github.com/slab-nlp/multi-prompt-llm-evaluation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"state-of-what-art-a-call-for-multi-prompt-llm","repo_url":"https://github.com/felipemaiapolo/prompteval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.00595","atlas_url":"https://app.syntology.ai/?focus=2401.00595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00595"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/felipemaiapolo/prompteval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/slab-nlp/multi-prompt-llm-evaluation","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":4},"by_repo_kind":{"official":{"samples":3,"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":5,"samples":[{"code_sha256_prefix":"aa8b6cfacbbfd0f8","entry":"flatten","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"aa8b6cfacbbfd0f8"}},{"code_sha256_prefix":"808a0054b649c466","entry":"get_directories_in_folder","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"808a0054b649c466"}},{"code_sha256_prefix":"3692d9f52dc4101c","entry":"get_default_prompts_and_hints","repo":"slab-nlp/multi-prompt-llm-evaluation","repo_kind":"official","path":"code/prompt_generation.py","file_url":"https://github.com/slab-nlp/multi-prompt-llm-evaluation/blob/HEAD/code/prompt_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3692d9f52dc4101c"}},{"code_sha256_prefix":"91268acce90f991e","entry":"get_prompt_format","repo":"slab-nlp/multi-prompt-llm-evaluation","repo_kind":"official","path":"code/prompt_generation.py","file_url":"https://github.com/slab-nlp/multi-prompt-llm-evaluation/blob/HEAD/code/prompt_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91268acce90f991e"}},{"code_sha256_prefix":"66963ee8a669de10","entry":"insert_prompt_row","repo":"slab-nlp/multi-prompt-llm-evaluation","repo_kind":"official","path":"code/prompt_generation.py","file_url":"https://github.com/slab-nlp/multi-prompt-llm-evaluation/blob/HEAD/code/prompt_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66963ee8a669de10"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}