SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.14564 · 2023

Language Models Hallucinate, but May Excel at Fact Verification

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 3 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/2310.14564.json · badge: /api/ran/2310.14564.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
jianguanthu/llmforfv canonical (classifier label)
classifier basis: census
6 ran · 3 no recorded run
FunctionStatusWhere it lives
acc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jianguanthu/llmforfv/code/metric.py
pointer only (licence: NONE) · get_code("74d38464e5b1a718")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/llmforfv when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

compute_precision_recall_per_threshold Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jianguanthu/llmforfv/code/meta_evaluation_lib.py
pointer only (licence: NONE) · get_code("ef3019c5908f32d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/llmforfv when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

expected_calibration_error Ran
ran; our contract draft was wrong, not the code
jianguanthu/llmforfv/code/metric.py
pointer only (licence: NONE) · get_code("241c78299ce539d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/llmforfv when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_optimal_gmeans_threshold Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jianguanthu/llmforfv/code/meta_evaluation_lib.py
pointer only (licence: NONE) · get_code("891a0a1f0f9c0727")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/llmforfv when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_predicted_labels Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jianguanthu/llmforfv/code/meta_evaluation_lib.py
pointer only (licence: NONE) · get_code("49f3a8d4ecf2178f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/llmforfv when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

std Ran
ran, honoured the contract we drafted
jianguanthu/llmforfv/code/metric.py
pointer only (licence: NONE) · get_code("4062d386ad3ef251")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/llmforfv when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

completion_with_backoff Not yet run
unverified (harvested, no recorded run)
jianguanthu/llmforfv/code/eval_flant5.py
pointer only (licence: NONE) · get_code("168cdb58f16242e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/llmforfv when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

meta_pro_direct Not yet run
unverified (harvested, no recorded run)
jianguanthu/llmforfv/code/meta_eval.py
pointer only (licence: NONE) · get_code("bc815d8fcd3f6e62")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/llmforfv when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

trunct Not yet run
unverified (harvested, no recorded run)
jianguanthu/llmforfv/code/eval_flant5.py
pointer only (licence: NONE) · get_code("b2cc9b358b0b170f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/llmforfv when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

FunctionAlso present inEarliest-datedOthers named
compute_precision_recall_per_threshold 1 other paper
1 dated earlier
2204.04991 (2022-04)
TRUE: Re-evaluating Factual Consistency Evaluation
get_optimal_gmeans_threshold 1 other paper
1 dated earlier
2204.04991 (2022-04)
TRUE: Re-evaluating Factual Consistency Evaluation
get_predicted_labels 1 other paper
1 dated earlier
2204.04991 (2022-04)
TRUE: Re-evaluating Factual Consistency Evaluation

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

Recent progress in natural language processing (NLP) owes much to remarkable advances in large language models (LLMs). Nevertheless, LLMs frequently "hallucinate," resulting in non-factual outputs. Our carefully-designed human evaluation substantiates the serious hallucination issue, revealing that even GPT-3.5 produces factual outputs less than 25% of the time. This underscores the importance of fact verifiers in order to measure and incentivize progress. Our systematic investigation affirms that LLMs can be repurposed as effective fact verifiers with strong correlations with human judgments. Surprisingly, FLAN-T5-11B, the least factual generator in our study, performs the best as a fact verifier, even outperforming more capable LLMs like GPT3.5 and ChatGPT. Delving deeper, we analyze the reliance of these LLMs on high-quality evidence, as well as their deficiencies in robustness and generalization ability. Our study presents insights for developing trustworthy generation models.

For agents

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

get_harvested_code_for_paper("2310.14564")
get_code_for_paper("2310.14564")
have("2310.14564")

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

curl https://syntology.ai/api/ran/2310.14564.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.14564.svg)](https://syntology.ai/paper/2310.14564)

Connect an agent — have() is free.