Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910258056658944 |
|---|---|
| author | Wang, Yingshuo Sun, Xian Li, Yanhang Fan, Zhichao Zhuang, Zexin |
| author_facet | Wang, Yingshuo Sun, Xian Li, Yanhang Fan, Zhichao Zhuang, Zexin |
| contents | Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price sometimes increases predicted demand, and implied willingness-to-pay estimates are frequently negative or implausible. We propose a two-stage adapter that embeds foundation model predictions within a utility-maximization framework. In the first stage, we estimate a standard choice model whose parameters are constrained to obey economic theory. In the second stage, we freeze those parameters and train a correction term that incorporates the foundation model's predictions as additional information. The result is a model that inherits the foundation model's accuracy gains while guaranteeing monotonic price-demand relationships under policy perturbation and producing analytically computable trade-off measures. On two transportation datasets, the adapter recovers up to 13 percentage points of accuracy over a standard logit model while maintaining perfect economic consistency, something neither the raw foundation models nor conventional distillation achieve. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_26559 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice Wang, Yingshuo Sun, Xian Li, Yanhang Fan, Zhichao Zhuang, Zexin Machine Learning Artificial Intelligence Econometrics Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price sometimes increases predicted demand, and implied willingness-to-pay estimates are frequently negative or implausible. We propose a two-stage adapter that embeds foundation model predictions within a utility-maximization framework. In the first stage, we estimate a standard choice model whose parameters are constrained to obey economic theory. In the second stage, we freeze those parameters and train a correction term that incorporates the foundation model's predictions as additional information. The result is a model that inherits the foundation model's accuracy gains while guaranteeing monotonic price-demand relationships under policy perturbation and producing analytically computable trade-off measures. On two transportation datasets, the adapter recovers up to 13 percentage points of accuracy over a standard logit model while maintaining perfect economic consistency, something neither the raw foundation models nor conventional distillation achieve. |
| title | Auditing and Fixing Economic Validity in Tabular Foundation Models for Discrete Choice |
| topic | Machine Learning Artificial Intelligence Econometrics |
| url | https://arxiv.org/abs/2605.26559 |