cs.CLNov 5, 2026

Decodability Is Not Validity: Evaluating Nuisance Sensitivity in Language Model Concept Probes

Authors: Ayal Klein

Abstract

Two concept probes can be equally accurate at predicting a concept from a language model's hidden states while their scores contain different mixtures of the target concept and a correlated nuisance attribute. In four target--nuisance settings (two aspect sentiments in CEBaB; occupation and gender in BiasBios; Amazon review sentiment with negation, and with first-person framing), two LLMs, and a population of concept extractors, we compare decodability with discriminant evidence: the score's dependence on the nuisance at fixed target, and its response to input edits intended to change only the nuisance, filtered by two LLM judges and compared against placebo edits. Under correlated training data, extractors that are statistically equivalent in held-out AUROC differ up to several-fold in nuisance sensitivity in three of the four settings, and decodability is not a reliable proxy for it: their rank correlation changes sign across settings. The effect follows the probe's training data, not the nuisance's natural association with the target: first-person framing, unrelated to sentiment in natural reviews, is absorbed at least as much as negation, which co-occurs with negative sentiment, and decorrelated training removes the systematic effect. Selecting extractors with nuisance-aware development diagnostics, which need nuisance labels but no counterfactuals, lowers counterfactual nuisance sensitivity wherever the default choice is sensitive, at a small accuracy cost. Concept measurements should be validated, not just decoded.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models

    Sep 4, 2026Gnaneswar Villuri, Hashmath Shaik, Alex DoboliLLM AuditingLanguage Model Calibration

  2. Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax

    Sep 24, 2026Zhenyan Lu, He Wang, Xiaohui HuangLLM EvaluationLanguage Model Decoding