Yingshuo Wang, Xian Sun, Yanhang Li, Zhichao Fan, Zexin Zhuang
arXiv 24 Jun 2026 · Machine Learning
arXiv:2606.26432 · PDF · DOI · OpenAlex · Extracted main text
Tabular foundation models achieve strong accuracy on choice prediction tasks, but their predictions often violate the economic logic those tasks require: raising a price can increase predicted demand, implied willingness-to-pay estimates are frequently negative or implausible, and unavailable alternatives receive nonzero probability. We propose a two-stage adapter that takes a foundation model's predicted choice probabilities as a precomputed feature and embeds them inside a multinomial logit's utility. In Stage 1, we fit the multinomial logit's structural coefficients by maximum likelihood with sign constraints; in Stage 2, we freeze those coefficients and fit a small neural correction operating on the foundation model's predictions. We prove that this composition exactly preserves the multinomial logit's marginal rate of substitution, so analytically computable value-of-time becomes a mathematical guarantee rather than an empirical accident. Across three datasets and two foundation models, the adapter gains 6.4 percentage points (pp) of test accuracy on average over the multinomial logit and up to 12.8 pp, maintains 100% cost monotonicity, and produces values of time within the published transportation-economics range on the transportation datasets. Performance degrades gracefully under foundation-model context restriction, retaining at least 6 pp of accuracy gain even at 10% of the original foundation-model context.
appendix boundary found by appendix_command · 67% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Ben-Akiva, Moshe and Lerman, Steven R (1985) Discrete Choice Analysis: Theory and Application to Travel Demand | 0.928 | 4 | 3 | 100% |
| 2 | Sartor, Davide and Sinigaglia, Alberto and Susto, Gian Antonio (2025) Advancing constrained monotonic neural networks: Achieving universal approximation beyond bounded activations | 0.843 | 3 | 3 | 100% |
| 3 | Hollmann, Noah and Müller, Samuel and Eggensperger, Katharina and Hu… (2023) TabPFN: A transformer that solves small tabular classification problems in a second | 0.843 | 3 | 3 | 100% |
| 4 | Hollmann, Noah and Müller, Samuel and Purucker, Lennart and Krishnak… (2025) Accurate predictions on small data with a tabular foundation model | 0.843 | 3 | 3 | 100% |
| 5 | Maddix Robinson, Danielle and Yin, Junming and Erickson, Nick and An… (2025) Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models self | 0.843 | 3 | 3 | 100% |
| 6 | Hillel, Tim and Bierlaire, Michel and Elshafie, Mohammed Z. E. B. an… (2021) A systematic review of machine learning classification methodologies for modelling passenger mode choice | 0.644 | 2 | 2 | 100% |
| 7 | Hinton, Geoffrey and Vinyals, Oriol and Dean, Jeff (2015) Distilling the knowledge in a neural network | 0.644 | 2 | 2 | 100% |
| 8 | Sill, Joseph (1997) Monotonic networks | 0.644 | 2 | 2 | 100% |
| 9 | van Cranenburgh, Sander and Wang, Sheng and Vij, Akshay and Pereira,… (2022) Choice modelling in the age of machine learning–-discussion paper | 0.644 | 2 | 2 | 100% |
| 10 | Wehenkel, Antoine and Louppe, Gilles (2019) Unconstrained monotonic neural networks | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 21 scored citations.