Papers › Ask Me Anything: A simple strategy for prompting language models

Ask Me Anything: A simple strategy for prompting language models

5 Oct 2022arXiv:2210.02441archive 2025-07-28

Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, Christopher Ré

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

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 2 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hazyresearch/ama_prompting officialmentioned in papermentioned on GitHubSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
simran-arora/focus mentioned on GitHubpytorchSyntology: not harvested report
simran-arora/privacy_fm mentioned on GitHubpytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

2 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong

Licence: 0 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hazyresearch/ama_prompting. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

hazyresearch/ama_prompting official repository 2 samples, 2 ran (2 instrument-failed) · 0 unverified
get_data in 223 papers boosting/run_ws.py ran · our draft was wrong Apache-2.0 (permissive) · 7fd190ceb6d35635 · report fixture: signature task_name:str/0/str, data_dir:str/0/str, model_prefix:str/0/str, override_date:str/0/str · returned tuple · level recorded 2026-09-22
get_top_deps_from_inverse_sig boosting/run_ws.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cb9e92364902e539 · report fixture: signature J:ndarray/2/float, k:int/0/int · returned list · level recorded 2026-09-22

Tasks

Coreference ResolutionNatural Language InferencePrompt EngineeringQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Coreference Resolution Winograd Schema Challenge Neo-6B (QA + WS) Accuracy 77.9 #25 of 82 Archive leaderboard report
Coreference Resolution Winograd Schema Challenge Neo-6B (QA) Accuracy 74.7 #27 of 82 Archive leaderboard report
Coreference Resolution Winograd Schema Challenge Neo-6B (few-shot) Accuracy 36.5 #80 of 82 Archive leaderboard report
Natural Language Inference RTE Neo-6B (QA + WS) Accuracy 75.1% #43 of 90 Archive leaderboard report
Natural Language Inference RTE Neo-6B (QA) Accuracy 61.7% #70 of 90 Archive leaderboard report
Natural Language Inference RTE Neo-6B (few-shot) Accuracy 58.8% #75 of 90 Archive leaderboard report
Question Answering BoolQ Neo-6B (QA + WS) Accuracy 67.2 #44 of 65 Archive leaderboard report
Question Answering BoolQ Neo-6B (few-shot) Accuracy 66.5 #46 of 65 Archive leaderboard report
Question Answering BoolQ Neo-6B (QA) Accuracy 64.9 #48 of 65 Archive leaderboard report
Question Answering COPA Neo-6B (QA + WS) Accuracy 84.0 #31 of 60 Archive leaderboard report
Question Answering COPA Neo-6B (few-shot) Accuracy 77.0 #41 of 60 Archive leaderboard report
Question Answering COPA Neo-6B (QA) Accuracy 58.2 #58 of 60 Archive leaderboard report
Question Answering MultiRC Neo-6B (QA + WS) F1 63.8 #17 of 30 Archive leaderboard report
Question Answering MultiRC Neo-6B (few-shot) F1 60.8 #20 of 30 Archive leaderboard report
Question Answering MultiRC Neo-6B (QA) F1 58.8 #22 of 30 Archive leaderboard report
Question Answering Natural Questions Neo-6B (QA) EM 19.7 #45 of 47 Archive leaderboard report
Question Answering Natural Questions Neo-6B (QA + WS) EM 19.6 #46 of 47 Archive leaderboard report
Question Answering Natural Questions Neo-6B (Few-Shot) EM 13.7 #47 of 47 Archive leaderboard report
Question Answering Story Cloze Neo-6B (QA + WS) Accuracy 87.8 #1 of 7 Archive leaderboard report
Question Answering Story Cloze Neo-6B (QA) Accuracy 76.3 #6 of 7 Archive leaderboard report
Question Answering Story Cloze Neo-6B (few-shot) Accuracy 51.0 #7 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

OPT

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections