Papers › REX: Reasoning-aware and Grounded Explanation

REX: Reasoning-aware and Grounded Explanation

11 Mar 2022CVPR 2022 1arXiv:2203.06107archive 2025-07-28

Shi Chen, Qi Zhao

Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the rationales behind the decisions. As a result, they commonly take advantage of spurious biases instead of actually reasoning on the visual-textual data, and have yet developed the capability to explain their decision making by considering key information from both modalities. This paper aims to close the gap from three distinct perspectives: first, we define a new type of multi-modal explanations that explain the decisions by progressively traversing the reasoning process and grounding keywords in the images. We develop a functional program to sequentially execute different reasoning steps and construct a new dataset with 1,040,830 multi-modal explanations. Second, we identify the critical need to tightly couple important components across the visual and textual modalities for explaining the decisions, and propose a novel explanation generation method that explicitly models the pairwise correspondence between words and regions of interest. It improves the visual grounding capability by a considerable margin, resulting in enhanced interpretability and reasoning performance. Finally, with our new data and method, we perform extensive analyses to study the effectiveness of our explanation under different settings, including multi-task learning and transfer learning. Our code and data are available at https://github.com/szzexpoi/rex.

PaperPDFConference PDFCodeCode 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="2203.06107")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

szzexpoi/rex officialmentioned in paperpytorch 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

2 samples harvested; 2 ran; 0 honoured the contract we drafted; 0 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.

2ran

Licence: 0 of the 2 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 szzexpoi/rex. “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.

GRU szzexpoi/rex/model/model/bert_exp.py official repository ran MIT (permissive) · 7fa4ae37ba493038 · report
VisualBert_REX szzexpoi/rex/model/model/bert_exp.py official repository ran MIT (permissive) · 23d8063bc44a1ed2 · report

Tasks

Decision MakingExplanation GenerationExplanatory Visual Question AnsweringFS-MEVQAMulti-Task LearningTransfer LearningVisual GroundingVisual Reasoning

Datasets

Introduced by this paper, per the archive.

GQA-REX

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Explanatory Visual Question Answering GQA-REX REX-LXMERT BLEU-4 54.79 #2 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-LXMERT CIDEr 466.01 #2 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-LXMERT GQA-test 58.15 #2 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-LXMERT GQA-val 78.19 #2 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-LXMERT Grounding 70.79 #2 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-LXMERT METEOR 39.51 #2 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-LXMERT ROUGE-L 79.41 #2 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-LXMERT SPICE 49.98 #2 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-VisualBert BLEU-4 54.59 #3 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-VisualBert CIDEr 464.20 #3 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-VisualBert GQA-test 57.77 #3 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-VisualBert GQA-val 66.16 #3 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-VisualBert Grounding 67.95 #3 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-VisualBert METEOR 39.22 #3 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-VisualBert ROUGE-L 78.56 #3 of 5 Archive leaderboard report
Explanatory Visual Question Answering GQA-REX REX-VisualBert SPICE 46.80 #3 of 5 Archive leaderboard report
FS-MEVQA SME REX #Learning Samples (N) 16 #7 of 7 Archive leaderboard report
FS-MEVQA SME REX ACC 17.77 #7 of 7 Archive leaderboard report
FS-MEVQA SME REX BLEU-4 0.00 #7 of 7 Archive leaderboard report
FS-MEVQA SME REX CIDEr 0.89 #7 of 7 Archive leaderboard report
FS-MEVQA SME REX Detection 0.00 #7 of 7 Archive leaderboard report
FS-MEVQA SME REX METEOR 4.37 #7 of 7 Archive leaderboard report
FS-MEVQA SME REX ROUGE-L 23.23 #7 of 7 Archive leaderboard report
FS-MEVQA SME REX SPICE 0.00 #7 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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