# TICDA: Tabular In-Context Data Attribution

arXiv: https://arxiv.org/abs/2610.07996 · HTML: https://mlsanity.com/paper/2610.07996/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 39 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 6 of 6)

- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [TabICLv2: A better, faster, scalable, and open tabular foundation model](https://mlsanity.com/paper/2602.11139/) (2026)
- [Beyond IID: How General Are Tabular Foundation Models, Really?](https://mlsanity.com/paper/2606.30410/) (2026)
- [TabPFN-3: Technical Report](https://mlsanity.com/paper/2605.13986/) (2026)
- [TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference](https://mlsanity.com/paper/2603.14171/) (2026)
- [TabPFN-3.5: Technical Report](https://mlsanity.com/paper/2609.17895/) (2026)

## Abstract (arXiv)

Tabular foundation models (TFMs) achieve strong predictive performance by conditioning on labeled demonstrations provided in context, without any parameter update. Yet how individual demonstrations shape a given prediction remains poorly understood. This gap matters in practice: the context is often assembled from whatever labeled data is available, potentially leading to the inclusion of mislabeled, redundant, or low-quality examples that degrade performance. Standard data attribution methods do not transfer to the TFM setting: resampling-based approaches such as DemoShapley require a combinatorial number of forward passes, and gradient-based estimators such as influence functions require computing training point's effect on the model parameters, which in-context learning never updates. We introduce TICDA, a method that measures the influence of every demonstration in the context directly from linear surrogates trained on TFM latent embeddings, in a single forward pass and at negligible cost. We show that TICDA offers the best compromise against competitors across four tasks: detecting labeling errors, curating context to preserve predictive accuracy while lowering inference cost, producing attribution scores that transfer across TFMs, and supporting an acquisition strategy for efficient active learning.