Pith. sign in

REVIEW 1 cited by

Selection Bias Induced Spurious Correlations in Large Language Models

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 2207.08982 v1 pith:GRLAU6I5 submitted 2022-07-18 cs.CL cs.AI

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

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this work we show how large language models (LLMs) can learn statistical dependencies between otherwise unconditionally independent variables due to dataset selection bias. To demonstrate the effect, we developed a masked gender task that can be applied to BERT-family models to reveal spurious correlations between predicted gender pronouns and a variety of seemingly gender-neutral variables like date and location, on pre-trained (unmodified) BERT and RoBERTa large models. Finally, we provide an online demo, inviting readers to experiment further.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. 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...

Pith tools