Papers › CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and...

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification

19 Mar 2025CVPR 2025 1arXiv:2503.15234archive 2025-07-28

Wenlong Yu, Qilong Wang, Chuang Liu, Dong Li, QinGhua Hu

Explainability is a critical factor influencing the wide deployment of deep vision models (DVMs). Concept-based post-hoc explanation methods can provide both global and local insights into model decisions. However, current methods in this field face challenges in that they are inflexible to automatically construct accurate and sufficient linguistic explanations for global concepts and local circuits. Particularly, the intrinsic polysemanticity in semantic Visual Concepts (VCs) impedes the interpretability of concepts and DVMs, which is underestimated severely. In this paper, we propose a Chain-of-Explanation (CoE) approach to address these issues. Specifically, CoE automates the decoding and description of VCs to construct global concept explanation datasets. Further, to alleviate the effect of polysemanticity on model explainability, we design a concept polysemanticity disentanglement and filtering mechanism to distinguish the most contextually relevant concept atoms. Besides, a Concept Polysemanticity Entropy (CPE), as a measure of model interpretability, is formulated to quantify the degree of concept uncertainty. The modeling of deterministic concepts is upgraded to uncertain concept atom distributions. Finally, CoE automatically enables linguistic local explanations of the decision-making process of DVMs by tracing the concept circuit. GPT-4o and human-based experiments demonstrate the effectiveness of CPE and the superiority of CoE, achieving an average absolute improvement of 36% in terms of explainability scores.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 13 ran (7 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

YuWLong666/CoE officialmentioned on GitHubpytorchBSD-3-ClauseSyntology: 15 samples, 13 ran (6 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
1ran; the contract check could not run
7ran
2unverified

Licence: 5 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from YuWLong666/CoE. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

YuWLong666/CoE official repository 15 samples, 13 ran (6 instrument-failed) · 2 unverified
all_gather in 119 papers util/misc.py ran · our draft was wrong BSD-3-Clause (permissive) here; the stored copy is pointer only · aa6da43d05cfaf65 · report fixture: signature data:dict/0/? · returned list · level recorded 2026-09-24
build_transform in 170 papers models/internvl.py ran · our draft was wrong BSD-3-Clause (permissive) · 57e95166ade5f25c · report fixture: signature input_size:int/0/int · returned Compose · level recorded 2026-09-24
check_folder in 7 papers polysemantic_eval.py ran fingerprinted BSD-3-Clause (permissive) · f4007627e1cb8260 · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-24
context_entails_response semantic_entropy.py ran BSD-3-Clause (permissive) · d29adfeb0ea0baf0 · report fixture: signature context:str/0/str, responses:list/1/str, model:callable/0/?, example:NoneType/0/? · returned float64 · level recorded 2026-09-25
dynamic_preprocess in 40 papers models/internvl.py ran · our draft was wrong BSD-3-Clause (permissive) here; the stored copy is pointer only · d610b5eabe0c9db1 · report fixture: signature image:Image/0/?, min_num:int/0/int, max_num:int/0/int, image_size:int/0/int, use_thumbnail:bool/0/bool · returned list · level recorded 2026-09-22
encode_image in 131 papers closeai.py ran · our draft was wrong BSD-3-Clause (permissive) here; the stored copy is pointer only · f41cb1a19b154297 · report fixture: signature image_path:str/0/str · returned str · level recorded 2026-09-22
entropy_loss_func util/misc.py ran fingerprinted BSD-3-Clause (permissive) · 0a889e98f9adc412 · report fixture: signature input_:Tensor/2/float · returned Tensor · level recorded 2026-09-24
find_closest_aspect_ratio in 45 papers models/internvl.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed BSD-3-Clause (permissive) here; the stored copy is pointer only · bd77f5f8067f18e9 · report fixture: signature aspect_ratio:float/0/float, target_ratios:list/1/tuple, width:int/0/int, height:int/0/int, image_size:int/0/int · returned tuple · level recorded 2026-09-22
get_args_parser in 9 papers parser.py ran BSD-3-Clause (permissive) · a628613dbdd55286 · report fixture: signature stages:list/1/str · returned ArgumentParser · level recorded 2026-09-24
get_semantic_ids semantic_entropy.py ran BSD-3-Clause (permissive) · 0635b0e8c158742e · report fixture: signature strings_list:list/1/str, model:callable/0/?, strict_entailment:bool/0/bool, example:NoneType/0/? · returned list · level recorded 2026-09-24
logsumexp_by_id semantic_entropy.py ran BSD-3-Clause (permissive) · 1ac9c618cee6223f · report fixture: signature semantic_ids:list/1/int, log_likelihoods:ndarray/1/float, agg:str/0/str · returned list · level recorded 2026-09-24
read_csv in 60 papers util/plot_utils.py ran BSD-3-Clause (permissive) · e53736b8f5970f9c · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-24
reduce_dict in 73 papers util/misc.py ran · our draft was wrong BSD-3-Clause (permissive) here; the stored copy is pointer only · 05992505df9ef0cd · report fixture: signature input_dict:dict/0/?, average:bool/0/bool · returned dict · level recorded 2026-09-24
basicset_logger util/loggerset.py unverified BSD-3-Clause (permissive) · 5636ff5ce8a9e959 · report
get_response in 48 papers closeai.py unverified BSD-3-Clause (permissive) · 43fb79dfb73bea95 · report

Tasks

Disentanglement

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CPE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections