SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.11863 · 2024

How Interpretable are Reasoning Explanations from Prompting Large Language Models?

arXiv · PDF · Open in the Atlas

Code that ran

13 of 16 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, 1 violated it and 1 has no contract verdict; 10 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/2402.11863.json · badge: /api/ran/2402.11863.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
wj210/cot_interpretability canonical (classifier label)
classifier basis: census
13 ran · 3 no recorded run
FunctionStatusWhere it lives
create_entailment_prompt Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/template/prompt_template.py
pointer only (licence: NONE) · get_code("46a8fc7b8d455553")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

cross_check_ans Ran
ran, violated the contract we drafted
wj210/cot_interpretability/openai_gen.py
pointer only (licence: NONE) · get_code("c010705f29317501")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

format_explanation Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/utils/data_collator_pinto.py
pointer only (licence: NONE) · get_code("882636a19c02bd1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

format_input Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/utils/data_collator_pinto.py
pointer only (licence: NONE) · get_code("9bac83066a04172a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

format_llama_prompt Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/template/prompt_template.py
pointer only (licence: NONE) · get_code("d9e7d08864a2514a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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_label Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/openai_gen.py
pointer only (licence: NONE) · get_code("9f162717bd58428a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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_label_tensor Ran
ran, honoured the contract we drafted
wj210/cot_interpretability/utils/data_collator_pinto.py
pointer only (licence: NONE) · get_code("d9efb3b6e8fe970a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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_logger Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/utils/utils.py
pointer only (licence: NONE) · get_code("91902d78bfbae499")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

preprocess_all Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/utils/utils.py
pointer only (licence: NONE) · get_code("4e7d204fa2924e1e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

preprocess_input Ran
ran on a synthesized input
wj210/cot_interpretability/utils/utils.py
pointer only (licence: NONE) · get_code("5ff002e9bf012277")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

process_answer Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/template/refine_template.py
pointer only (licence: NONE) · get_code("9e0cd81e8cf96360")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

process_feedback Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/template/refine_template.py
pointer only (licence: NONE) · get_code("6b43934be1427d31")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

prompt_input Ran
ran; our contract draft was wrong, not the code
wj210/cot_interpretability/template/prompt_template.py
pointer only (licence: NONE) · get_code("23df1880ebfb46ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

clear_pad Not yet run
unverified (harvested, no recorded run)
wj210/cot_interpretability/utils/model_utils.py
pointer only (licence: NONE) · get_code("f86199c589be7bff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

faithfulness_test Not yet run
unverified (harvested, no recorded run)
wj210/cot_interpretability/utils/model_utils.py
pointer only (licence: NONE) · get_code("78211d8377e50f1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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.

load_raw_dataset Not yet run
unverified (harvested, no recorded run)
wj210/cot_interpretability/utils/data_helper.py
pointer only (licence: NONE) · get_code("b2d1503e1d9306ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wj210/cot_interpretability 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 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 15 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
get_logger 1 other paper
1 dated earlier
2112.06318 (2021-12)
Contextualized Scene Imagination for Generative Commonsense Reasoning

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

Prompt Engineering has garnered significant attention for enhancing the performance of large language models across a multitude of tasks. Techniques such as the Chain-of-Thought not only bolster task performance but also delineate a clear trajectory of reasoning steps, offering a tangible form of explanation for the audience. Prior works on interpretability assess the reasoning chains yielded by Chain-of-Thought solely along a singular axis, namely faithfulness. We present a comprehensive and multifaceted evaluation of interpretability, examining not only faithfulness but also robustness and utility across multiple commonsense reasoning benchmarks. Likewise, our investigation is not confined to a single prompting technique; it expansively covers a multitude of prevalent prompting techniques employed in large language models, thereby ensuring a wide-ranging and exhaustive evaluation. In addition, we introduce a simple interpretability alignment technique, termed Self-Entailment-Alignment Chain-of-thought, that yields more than 70\% improvements across multiple dimensions of interpretability. Code is available at https://github.com/SenticNet/CoT_interpretability

For agents

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

get_harvested_code_for_paper("2402.11863")
get_code_for_paper("2402.11863")
have("2402.11863")

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

curl https://syntology.ai/api/ran/2402.11863.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.11863.svg)](https://syntology.ai/paper/2402.11863)

Connect an agent — have() is free.