Estimand-Relative Validity and Context-Driven Instability of Shapley Explanations for Tabular Foundation Models

Abstract Shapley explanations for tabular foundation models depend on a removal operator that determines how predictions are evaluated when features are absent. Although different operators induce different cooperative games, their effects on attribution validity and stability in in-context tabular models remain insufficiently understood. We compare five removal operators for TabPFN v2 and TabICL v2 using exact Shapley enumeration, controlled synthetic data with known or high-precision reference attributions, real-world tabular datasets, and a preregistered factorial design. Operator performance was strongly estimand-dependent. Mean imputation and missing-value encoding most closely approximated interventional attributions, whereas recontextualisation and conditional estimation through in-context learning yielded the lowest errors for the conditional estimand; these rankings also varied with feature dependence. Across nuisance configurations, attribution variability was dominated by the sampled in-context examples, while column order, label coding, and model seed contributed little. A planted-null-feature control further showed that both models frequently changed their predictions in response to features constructed to contain no label information. The analysis is limited to two binary-classification foundation models and exact enumeration in low-dimensional settings, so the observed rankings should not be extrapolated to larger feature spaces or other model families. These findings show that Shapley explanations for tabular foundation models are not interpretable without specifying both the removal operator and the intended estimand, and that context sensitivity should be reported as part of explanation reliability.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-12
DOI
https://doi.org/10.21203/rs.3.rs-11112632/v1
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Estimand-Relative Validity and Context-Driven Instability of Shapley Explanations for Tabular Foundation Models

Emin Talip Demirkiran
Research Square
Explainable Artificial Intelligence (XAI)
preprint

Estimand-Relative Validity and Context-Driven Instability of Shapley Explanations for Tabular Foundation Models

Emin Talip Demirkiran
preprint en

Abstract

Abstract Shapley explanations for tabular foundation models depend on a removal operator that determines how predictions are evaluated when features are absent. Although different operators induce different cooperative games, their effects on attribution validity and stability in in-context tabular models remain insufficiently understood. We compare five removal operators for TabPFN v2 and TabICL v2 using exact Shapley enumeration, controlled synthetic data with known or high-precision reference attributions, real-world tabular datasets, and a preregistered factorial design. Operator performance was strongly estimand-dependent. Mean imputation and missing-value encoding most closely approximated interventional attributions, whereas recontextualisation and conditional estimation through in-context learning yielded the lowest errors for the conditional estimand; these rankings also varied with feature dependence. Across nuisance configurations, attribution variability was dominated by the sampled in-context examples, while column order, label coding, and model seed contributed little. A planted-null-feature control further showed that both models frequently changed their predictions in response to features constructed to contain no label information. The analysis is limited to two binary-classification foundation models and exact enumeration in low-dimensional settings, so the observed rankings should not be extrapolated to larger feature spaces or other model families. These findings show that Shapley explanations for tabular foundation models are not interpretable without specifying both the removal operator and the intended estimand, and that context sensitivity should be reported as part of explanation reliability.

Research Square
Eskisehir Technical University (TR)
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