SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.07927 · 2024

Are self-explanations from Large Language Models faithful?

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 3 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/2401.07927.json · badge: /api/ran/2401.07927.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
AndreasMadsen/llm-introspection canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
latex_encode_newline Ran
ran; our contract draft was wrong, not the code
AndreasMadsen/llm-introspection/export/latex_prompt.py
pointer only (licence: NONE) · get_code("b4d882e4f359c087")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AndreasMadsen/llm-introspection 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.

tex_format_time Ran
ran; our contract draft was wrong, not the code
AndreasMadsen/llm-introspection/export/latex_compute.py
pointer only (licence: NONE) · get_code("c77fcfe1ed582097")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AndreasMadsen/llm-introspection 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.

tex_multirow Ran
ran; our contract draft was wrong, not the code
AndreasMadsen/llm-introspection/export/latex_compute.py
pointer only (licence: NONE) · get_code("43048920a3d808ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AndreasMadsen/llm-introspection 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.

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, 1 are also present in other papers whose code we hold (1 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.

FunctionAlso present inEarliest-datedOthers named
tex_format_time 1 other paper
1 dated earlier
2310.07819 (2023-10)
Faithfulness Measurable Masked Language Models

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

Instruction-tuned Large Language Models (LLMs) excel at many tasks and will even explain their reasoning, so-called self-explanations. However, convincing and wrong self-explanations can lead to unsupported confidence in LLMs, thus increasing risk. Therefore, it's important to measure if self-explanations truly reflect the model's behavior. Such a measure is called interpretability-faithfulness and is challenging to perform since the ground truth is inaccessible, and many LLMs only have an inference API. To address this, we propose employing self-consistency checks to measure faithfulness. For example, if an LLM says a set of words is important for making a prediction, then it should not be able to make its prediction without these words. While self-consistency checks are a common approach to faithfulness, they have not previously been successfully applied to LLM self-explanations for counterfactual, feature attribution, and redaction explanations. Our results demonstrate that faithfulness is explanation, model, and task-dependent, showing self-explanations should not be trusted in general. For example, with sentiment classification, counterfactuals are more faithful for Llama2, feature attribution for Mistral, and redaction for Falcon 40B.

For agents

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

get_harvested_code_for_paper("2401.07927")
get_code_for_paper("2401.07927")
have("2401.07927")

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

curl https://syntology.ai/api/ran/2401.07927.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.07927.svg)](https://syntology.ai/paper/2401.07927)

Connect an agent — have() is free.