SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.18404 · ICML · 2023

Conformal Prediction with Large Language Models for Multi-Choice Question Answering

Charles Lu, Ramesh Raskar, David Bellamy, Andrew Beam, Anil Palepu, Gauri Gupta, Bhawesh Kumar, Charlie Lu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 1 failure of our instrument; 2 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/2305.18404.json · badge: /api/ran/2305.18404.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
bhaweshiitk/conformalllm canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
get_prompt Ran
ran; our contract draft was wrong, not the code
bhaweshiitk/conformalllm/conformal_llm_scores.py
code served (permissive licence) · get_code("62b2e921ddd66bd8")
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 str. 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 torch
import numpy as np

torch.manual_seed(0)

# Construct task_data dict following MMLU structure
task_data = {
    'test': {
        'input': [
            'What is the capital of France?',
            'What is 2+2?',
            'Which planet is closest to the sun?'
        ],
        'A': [
            'London',
            '3',
            'Venus'
        ],
        'B': [
            'Paris',
            '4',
            'Mercury'
        ],
        'C': [
            'Berlin',
            '5',
            'Earth'
        ],
        'D': [
            'Madrid',
            '6',
            'Mars'
        ],
        'target': [
            'B',
            'B',
            'B'
        ]
    }
}

# Construct task name
task = 'world_capitals'

# Construct question_num
question_num = 0

# Construct prompt_q (optional, can be None)
prompt_q = None

ARGS = {
    'task_data': task_data,
    'task': task,
    'question_num': question_num,
    'prompt_q': prompt_q
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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_question_dict Not yet run
unverified (harvested, no recorded run)
bhaweshiitk/conformalllm/conformal_llm_scores.py
code served (permissive licence) · get_code("5d579a3b632ea394")
How it ran

no invocation recorded.

modify_task_data Not yet run
unverified (harvested, no recorded run)
bhaweshiitk/conformalllm/conformal_llm_scores.py
code served (permissive licence) · get_code("3171dbdc16c95bf0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

As large language models are widely developed, robust uncertainty quantification techniques will become crucial for safe deployment in highstakes scenarios. This work explores how conformal prediction can quantify uncertainty in language models for multiple-choice questionanswering. We find that the uncertainty estimates from conformal prediction are tightly correlated with prediction accuracy. This observation can be helpful in downstream applications such as selective classification and filtering out low-quality predictions. We also investigate the exchangeability assumption required by conformal prediction to out-of-subject questions, which may be a more realistic scenario for many practical applications. Our work contributes towards more trustworthy and reliable usage of large language models in safety-critical situations, where robust guarantees of error rate are required.

For agents

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

get_harvested_code_for_paper("2305.18404")
get_code_for_paper("2305.18404")
have("2305.18404")

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

curl https://syntology.ai/api/ran/2305.18404.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.18404.svg)](https://syntology.ai/paper/2305.18404)

Connect an agent — have() is free.