Papers › NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation

NeuroCounterfactuals: Beyond Minimal-Edit Counterfactuals for Richer Data Augmentation

22 Oct 2022arXiv:2210.12365archive 2025-07-28

Phillip Howard, Gadi Singer, Vasudev Lal, Yejin Choi, Swabha Swayamdipta

While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable inductive bias for models remains a challenge. Most existing approaches for producing counterfactuals, manual or automated, rely on small perturbations via minimal edits, resulting in simplistic changes. We introduce NeuroCounterfactuals, designed as loose counterfactuals, allowing for larger edits which result in naturalistic generations containing linguistic diversity, while still bearing similarity to the original document. Our novel generative approach bridges the benefits of constrained decoding, with those of language model adaptation for sentiment steering. Training data augmentation with our generations results in both in-domain and out-of-domain improvements for sentiment classification, outperforming even manually curated counterfactuals, under select settings. We further present detailed analyses to show the advantages of NeuroCounterfactuals over approaches involving simple, minimal edits.

PaperPDFCode

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

Code

intellabs/neurocounterfactuals officialmentioned in papernot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationDiversityInductive BiasLanguage ModelingLanguage ModellingSentiment AnalysisSentiment Classification

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.

Methods

Counterfactuals

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