Pith. sign in

REVIEW 3 cited by

Shortcut Learning of Large Language Models in Natural Language Understanding

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2208.11857 v2 pith:RFHR7JY6 submitted 2022-08-25 cs.CL cs.LG

Mengnan Du , Fengxiang He , Na Zou , Dacheng Tao , Xia Hu This is my paper
classification cs.CLcs.LG
keywords languagelearningshortcutllmsmodelsintroducelargenatural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. However, these LLMs might rely on dataset bias and artifacts as shortcuts for prediction. This has significantly affected their generalizability and adversarial robustness. In this paper, we provide a review of recent developments that address the shortcut learning and robustness challenge of LLMs. We first introduce the concepts of shortcut learning of language models. We then introduce methods to identify shortcut learning behavior in language models, characterize the reasons for shortcut learning, as well as introduce mitigation solutions. Finally, we discuss key research challenges and potential research directions in order to advance the field of LLMs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Mitigating Shortcut Learning with InterpoLated Learning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    InterpoLL improves minority generalization by interpolating representations of majority examples with intra-class minority examples during training.

  2. Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Across 35 models and two languages, language models perform at or below chance at telling possible-but-unlikely events from impossible ones when semantic relatedness conflicts with possibility.

  3. Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A token-discarding method for vision transformers measures whether predictions rely on features outside the object's bounding box, identifying spurious correlations and problematic ImageNet classes.

Pith tools