Pith. sign in

REVIEW 4 cited by

Linear Adversarial Concept Erasure

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 2201.12091 v8 pith:GBWTCE3M submitted 2022-01-28 cs.LG cs.CL

Linear Adversarial Concept Erasure

classification cs.LG cs.CL
keywords linearconceptmethodproblembiasincreasinglyremovalrepresentations
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in real-world applications, the inability to \emph{control} their content becomes an increasingly important problem. We formulate the problem of identifying and erasing a linear subspace that corresponds to a given concept, in order to prevent linear predictors from recovering the concept. We model this problem as a constrained, linear maximin game, and show that existing solutions are generally not optimal for this task. We derive a closed-form solution for certain objectives, and propose a convex relaxation, \method, that works well for others. When evaluated in the context of binary gender removal, the method recovers a low-dimensional subspace whose removal mitigates bias by intrinsic and extrinsic evaluation. We show that the method is highly expressive, effectively mitigating bias in deep nonlinear classifiers while maintaining tractability and interpretability.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. Emergent Misalignment Recruits a Pre-existing Persona Subspace

    cs.LG 2026-07 conditional novelty 7.0

    Fine-tuning on narrow bad data recruits a low-rank persona subspace already present in a frozen instruction-tuned model; holding that subspace out of activations prevents broad misalignment, and injecting it into the ...

  2. Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias

    cs.LG 2026-07 conditional novelty 6.5

    LLM-as-judge scoring biases concentrate in low-dimensional, type-specific activation subspaces that support bidirectional causal steering and cross-domain failure prediction.

  3. Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins

    cs.CL 2026-07 conditional novelty 6.0

    Small hyperbolic models (146M–3B) report 100% creative-seed preference, 90.7% compliance-gap detection, and a selective-gating skeleton–wallpaper memory pilot as a companion-AI stack.

  4. Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins

    cs.CL 2026-07 conditional novelty 6.0

    On the same 720 replies, scoring exposure versus manifestation shifts the auditor-judge gap by ~0.2 AUROC and can reverse their ranking, so single detection AUROCs are under-specified.