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

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 firstperson 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.

Authors

Publication Details

Published
2026-11-14
DOI
https://doi.org/10.66977/xsci.2611.0028
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

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

Ayal Klein
2 links
Explainable Artificial Intelligence (XAI)
preprint

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

Ayal Klein
preprint en

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 firstperson 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.

Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon