SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.02441 · 2022

Ask Me Anything: A simple strategy for prompting language models

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2210.02441.json · badge: /api/ran/2210.02441.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
hazyresearch/ama_prompting canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_data Ran
ran; our contract draft was wrong, not the code
hazyresearch/ama_prompting/boosting/run_ws.py
code served (permissive licence) · get_code("7fd190ceb6d35635")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import json
import tempfile
import numpy as np

# Create a temporary directory for test data
tmpdir = tempfile.mkdtemp()

# Create task directory
task_name = 'super_glue_rte'
task_dir = os.path.join(tmpdir, task_name)
os.makedirs(task_dir, exist_ok=True)

# Create mock data files
date = '01012024'
model_prefix = 'test_model'

# Create test data
test_data = {
    '0': {
        'example': 'test example 0',
        'gold': 'True',
        'preds_boost': ['True', 'False', 'True']
    },
    '1': {
        'example': 'test example 1',
        'gold': 'False',
        'preds_boost': ['False', 'True', 'False']
    }
}

# Create train data
train_data = {
    '0': {
        'example': 'train example 0',
        'gold': 'True',
        'preds_boost': ['True', 'False', 'True']
    },
    '1': {
        'example': 'train example 1',
        'gold': 'False',
        'preds_boost': ['False', 'True', 'False']
    }
}

# Write JSON files
test_file = os.path.join(task_dir, f'{model_prefix}_decomposed_{date}.json')
train_file = os.path.join(task_dir, f'{model_prefix}_decomposed_{date}_train.json')

with open(test_file, 'w') as f:
    json.dump(test_data, f)

with open(train_file, 'w') as f:
    json.dump(train_data, f)

ARGS = {
    'task_name': 'super_glue_rte',
    'data_dir': tmpdir,
    'model_prefix': 'test_model',
    'override_date': date
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_top_deps_from_inverse_sig Ran
ran; our contract draft was wrong, not the code
hazyresearch/ama_prompting/boosting/run_ws.py
code served (permissive licence) · get_code("cb9e92364902e539")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small test matrix J
# The function uses J.shape[0] to get m, and indexes into J with np.argsort
# So J should be a 2D numpy array
J = np.array([
    [0.5, 1.2, -0.3, 2.1],
    [0.8, -1.5, 0.9, 0.2],
    [-0.6, 0.4, 1.1, -0.7],
    [1.3, -0.5, 0.3, 0.6]
], dtype=np.float32)

# k is the number of top dependencies to extract
k = 5

ARGS = {
    "J": J,
    "k": k
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.02441")
get_code_for_paper("2210.02441")
have("2210.02441")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.02441.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.02441.svg)](https://syntology.ai/paper/2210.02441)

Connect an agent — have() is free.