Papers › Causal Proxy Models for Concept-Based Model Explanations

Causal Proxy Models for Concept-Based Model Explanations

28 Sep 2022arXiv:2209.14279archive 2025-07-28

Zhengxuan Wu, Karel D'Oosterlinck, Atticus Geiger, Amir Zur, Christopher Potts

Explainability methods for NLP systems encounter a version of the fundamental problem of causal inference: for a given ground-truth input text, we never truly observe the counterfactual texts necessary for isolating the causal effects of model representations on outputs. In response, many explainability methods make no use of counterfactual texts, assuming they will be unavailable. In this paper, we show that robust causal explainability methods can be created using approximate counterfactuals, which can be written by humans to approximate a specific counterfactual or simply sampled using metadata-guided heuristics. The core of our proposal is the Causal Proxy Model (CPM). A CPM explains a black-box model 𝒩 because it is trained to have the same actual input/output behavior as 𝒩 while creating neural representations that can be intervened upon to simulate the counterfactual input/output behavior of 𝒩. Furthermore, we show that the best CPM for 𝒩 performs comparably to 𝒩 in making factual predictions, which means that the CPM can simply replace 𝒩, leading to more explainable deployed models. Our code is available at https://github.com/frankaging/Causal-Proxy-Model.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2209.14279")

Code

Syntology Ran 1 of 5 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

frankaging/causal-proxy-model officialmentioned in papermentioned on GitHubpytorchMIT 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

5 samples harvested; 1 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran
4unverified

Licence: 0 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from frankaging/causal-proxy-model. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

create_position_ids_from_input_ids frankaging/causal-proxy-model/models/modelings_roberta.py official repository ran MIT (permissive) · 38f46ef4e03fee1c · report
flatten_logits frankaging/causal-proxy-model/experiments/libs.py official repository unverified MIT (permissive) · 7870de46dfa10c6a · report
get_iit_examples frankaging/causal-proxy-model/experiments/libs.py official repository unverified MIT (permissive) · fbb97c2606ded64b · report
load_tf_weights_in_bert frankaging/causal-proxy-model/models/modelings_bert.py official repository unverified MIT (permissive) · d009b630f4496e64 · report
query_with_aspect_label frankaging/causal-proxy-model/experiments/libs.py official repository unverified MIT (permissive) · b22b5b4b99d369e2 · report

Tasks

Causal Inferencemodel

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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