Metraipolis › archive › dc_50c256ee5a08
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers — arXiv:2608.09209
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09209
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:50:18.939Z
- SHA-256 of the archived text
fe36d21964189354666f02c53200b03d7182eef2e68c974d48fbc5cf00d59075- Stable URL of this page
https://metraipolis.com/documento/dc_50c256ee5a08
How to cite
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers — arXiv:2608.09209 — arXiv (en), https://arxiv.org/abs/2608.09209 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50c256ee5a08 (Metraipolis archive dc_50c256ee5a08, sha256 fe36d21964189354666f02c53200b03d7182eef2e68c974d48fbc5cf00d59075)
BibTeX
@misc{dc50c256ee5a08,
title = {UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers — arXiv:2608.09209},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09209},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50c256ee5a08; sha256 fe36d21964189354666f02c53200b03d7182eef2e68c974d48fbc5cf00d59075},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09209. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs. Existing approaches either require manual specification of the feature vocabulary or automate discovery only partially, leaving the gap between dataset-level correlation and model-level exploitation unaddressed. We present U N M ASK, a fully automated pipeline that discovers, causally verifies, and mitigates spurious correlations in text classifiers without additional human annotation. Given unlabeled training examples, U N M ASK generates candidate surface patterns as executable boolean expressions, filters them through a statistical validation protocol with independent replication, and establishes causal model dependence via verified counterfactual interventions. Causally confirmed features then serve as annotation-free group definitions for Deep Feature Reweighting, eliminating the group labels that standard DFR requires. Applied to BERT and RoBERTa trained on MNLI, our pipeline independently rediscovers established lexical-overlap and negation biases, verifying 9 of 10 features on BERT and 6 on RoBERTa, and improving HANS accuracy by up to 12.58 pp. On CivilComments-WILDS, programmatic groups match the 70.1% worst- group accuracy of hand-labeled DFR (Kirichenko et al., 2023) without demographic annotation. We further demonstrate that the discovery and validation stages generalize to reward model preference data, surfacing interpretable spurious correlations in RewardBench2. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.09209 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:49:41.920Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).