{"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/ask-me-anything-a-simple-strategy-for","title":"Ask Me Anything: A simple strategy for prompting language models","arxiv_id":"2210.02441","date":"2022-10-05","proceeding":null,"authors":["Simran Arora","Avanika Narayan","Mayee F. Chen","Laurel Orr","Neel Guha","Kush Bhatia","Ines Chami","Frederic Sala","Christopher Ré"],"abstract":"Large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt that demonstrates how to perform the task and no additional training. Prompting is a brittle process wherein small modifications to the prompt can cause large variations in the model predictions, and therefore significant effort is dedicated towards designing a painstakingly \"perfect prompt\" for a task. To mitigate the high degree of effort involved in prompt-design, we instead ask whether producing multiple effective, yet imperfect, prompts and aggregating them can lead to a high quality prompting strategy. Our observations motivate our proposed prompting method, ASK ME ANYTHING (AMA). We first develop an understanding of the effective prompt formats, finding that question-answering (QA) prompts, which encourage open-ended generation (\"Who went to the park?\") tend to outperform those that restrict the model outputs (\"John went to the park. Output True or False.\"). Our approach recursively uses the LLM itself to transform task inputs to the effective QA format. We apply the collected prompts to obtain several noisy votes for the input's true label. We find that the prompts can have very different accuracies and complex dependencies and thus propose to use weak supervision, a procedure for combining the noisy predictions, to produce the final predictions for the inputs. We evaluate AMA across open-source model families (e.g., EleutherAI, BLOOM, OPT, and T0) and model sizes (125M-175B parameters), demonstrating an average performance lift of 10.2% over the few-shot baseline. This simple strategy enables the open-source GPT-J-6B model to match and exceed the performance of few-shot GPT3-175B on 15 of 20 popular benchmarks. Averaged across these tasks, the GPT-J-6B model outperforms few-shot GPT3-175B. We release our code here: https://github.com/HazyResearch/ama_prompting","url_abs":"https://arxiv.org/abs/2210.02441v3","url_pdf":"https://arxiv.org/pdf/2210.02441v3.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":"ask-me-anything-a-simple-strategy-for","repo_url":"https://github.com/hazyresearch/ama_prompting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"ask-me-anything-a-simple-strategy-for","repo_url":"https://github.com/simran-arora/focus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"ask-me-anything-a-simple-strategy-for","repo_url":"https://github.com/simran-arora/privacy_fm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"opt","method_name":"OPT"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"Neo-6B (QA + WS)","rank_in_archive_order":25,"of":82,"metrics":{"Accuracy":"77.9"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"Neo-6B (QA)","rank_in_archive_order":27,"of":82,"metrics":{"Accuracy":"74.7"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"Neo-6B (few-shot)","rank_in_archive_order":80,"of":82,"metrics":{"Accuracy":"36.5"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"Neo-6B (QA + WS)","rank_in_archive_order":43,"of":90,"metrics":{"Accuracy":"75.1%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"Neo-6B (QA)","rank_in_archive_order":70,"of":90,"metrics":{"Accuracy":"61.7%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"Neo-6B (few-shot)","rank_in_archive_order":75,"of":90,"metrics":{"Accuracy":"58.8%"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-boolq","task":"Question Answering","dataset":"BoolQ","model":"Neo-6B (QA + WS)","rank_in_archive_order":44,"of":65,"metrics":{"Accuracy":" 67.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-boolq","task":"Question Answering","dataset":"BoolQ","model":"Neo-6B (few-shot)","rank_in_archive_order":46,"of":65,"metrics":{"Accuracy":"66.5"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-boolq","task":"Question Answering","dataset":"BoolQ","model":"Neo-6B (QA)","rank_in_archive_order":48,"of":65,"metrics":{"Accuracy":"64.9"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"Neo-6B (QA + WS)","rank_in_archive_order":31,"of":60,"metrics":{"Accuracy":"84.0"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"Neo-6B (few-shot)","rank_in_archive_order":41,"of":60,"metrics":{"Accuracy":"77.0"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-copa","task":"Question Answering","dataset":"COPA","model":"Neo-6B (QA)","rank_in_archive_order":58,"of":60,"metrics":{"Accuracy":"58.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-multirc","task":"Question Answering","dataset":"MultiRC","model":"Neo-6B (QA + WS)","rank_in_archive_order":17,"of":30,"metrics":{"F1":" 63.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-multirc","task":"Question Answering","dataset":"MultiRC","model":"Neo-6B (few-shot)","rank_in_archive_order":20,"of":30,"metrics":{"F1":"60.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-multirc","task":"Question Answering","dataset":"MultiRC","model":"Neo-6B (QA)","rank_in_archive_order":22,"of":30,"metrics":{"F1":"58.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-natural-questions","task":"Question Answering","dataset":"Natural Questions","model":"Neo-6B (QA)","rank_in_archive_order":45,"of":47,"metrics":{"EM":"19.7"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-natural-questions","task":"Question Answering","dataset":"Natural Questions","model":"Neo-6B (QA + WS)","rank_in_archive_order":46,"of":47,"metrics":{"EM":" 19.6"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-natural-questions","task":"Question Answering","dataset":"Natural Questions","model":"Neo-6B (Few-Shot)","rank_in_archive_order":47,"of":47,"metrics":{"EM":"13.7"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-story-cloze","task":"Question Answering","dataset":"Story Cloze","model":"Neo-6B (QA + WS)","rank_in_archive_order":1,"of":7,"metrics":{"Accuracy":"87.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-story-cloze","task":"Question Answering","dataset":"Story Cloze","model":"Neo-6B (QA)","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy":"76.3"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-story-cloze","task":"Question Answering","dataset":"Story Cloze","model":"Neo-6B (few-shot)","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy":"51.0"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2210.02441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02441"}},"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/hazyresearch/ama_prompting","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simran-arora/focus","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simran-arora/privacy_fm","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"7fd190ceb6d35635","entry":"get_data","repo":"hazyresearch/ama_prompting","repo_kind":"official","path":"boosting/run_ws.py","file_url":"https://github.com/hazyresearch/ama_prompting/blob/HEAD/boosting/run_ws.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7fd190ceb6d35635"}},{"code_sha256_prefix":"cb9e92364902e539","entry":"get_top_deps_from_inverse_sig","repo":"hazyresearch/ama_prompting","repo_kind":"official","path":"boosting/run_ws.py","file_url":"https://github.com/hazyresearch/ama_prompting/blob/HEAD/boosting/run_ws.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb9e92364902e539"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}