Pith. sign in

REVIEW 5 cited by

Explore Spurious Correlations at the Concept Level in Language Models for Text Classification

Not yet reviewed by Pith; the record is open.

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 2311.08648 v4 pith:D7HE2GQD submitted 2023-11-15 cs.CL cs.AI

classification cs.CLcs.AI
keywords conceptcorrelationsdatamodelsspuriouslabellanguagefine-tuning
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness challenges due to spurious correlations arising from imbalanced label distributions in training data or ICL exemplars. Previous research has primarily concentrated on word, phrase, and syntax features, neglecting the concept level, often due to the absence of concept labels and difficulty in identifying conceptual content in input texts. This paper introduces two main contributions. First, we employ ChatGPT to assign concept labels to texts, assessing concept bias in models during fine-tuning or ICL on test data. We find that LMs, when encountering spurious correlations between a concept and a label in training or prompts, resort to shortcuts for predictions. Second, we introduce a data rebalancing technique that incorporates ChatGPT-generated counterfactual data, thereby balancing label distribution and mitigating spurious correlations. Our method's efficacy, surpassing traditional token removal approaches, is validated through extensive testing.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail

    cs.LG 2025-12 conditional novelty 6.0 of 10

    Reliable concept presence in transformers is concentrated in the extreme high-activation tail of in-concept tokens; thresholding that tail improves concept detection and localization.

  2. CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models

    cs.CL 2025-09 conditional novelty 5.0 of 10

    A training method that injects token-level causal labels into attention improves out-of-distribution accuracy on a synthetic benchmark and slightly on math/reasoning tasks.

  3. MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs

    cs.CL 2025-02 conditional novelty 5.0 of 10

    Merging specialized LLMs into a MoE can be improved by replacing averaging with Dare/Ties merging and by using perplexity-based routing, while heterogeneous experts can be merged with projectors and a sequence-level router.

  4. Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

    cs.LG 2025-01 conditional novelty 5.0 of 10

    Causal reward modeling applies MMD regularization to RLHF reward models to make reward scores statistically independent of spurious features, reducing measured length, sycophancy, concept, and demographic biases in ex...

  5. Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration

    cs.LG 2025-09 conditional novelty 4.0 of 10

    Constraining LLM rewriting with a biomedical NER model improves medical entity preservation and reduces hallucinations in synthetic clinical notes, with modest downstream gains on MIMIC-III tasks.

Pith tools