Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models

A new approach called Auto-Fill, which post-trains three specialist small language models (SLMs) for world knowledge, text-based reasoning, and code-based reasoning, achieves superior accuracy in predicting missing cell values in tabular data compared to state-of-the-art reasoning models like o3-pro, Gemini 3 Pro, and DeepSeek R1, while operating at less than 1% of their cost. The method, developed by researchers and made publicly available on GitHub, uses a calibrated ensemble mechanism to dynamically select the most confident specialist or abstain, ensuring high precision across 11 benchmarks with 2,200 real tables.

arXiv:2607.19847v1 Announce Type: cross Abstract: Predicting missing cell values in tabular data is a fundamental problem in data cleaning. While state-of-the-art reasoning models show great promise in predicting missing values in tables, by reasoning holistically across rows and columns, they are costly to deploy at scale and tend to be overconfident, often generating hallucinated or false-positive predictions. In this paper, we observe that achieving high-precision missing-value prediction in tables requires a distinct combination of three capabilities: 1 world knowledge, 2 text-based reasoning, and 3 code-based reasoning. We systematically explore design choices for combining these capabilities, and propose an Auto-Fill approach that post-trains three specialist small language models SLMs , each optimized for one capability. We develop a calibrated ensemble mechanism that either dynamically selects the most confident specialist or abstains, ensuring high accuracy. Extensive experiments on 11 benchmarks with 2200 real tables drawn from diverse domains show that Auto-Fill achieves superior accuracy compared to state-of-the-art reasoning models e.g., o3-pro, Gemini 3 Pro, and DeepSeek R1 , while operating at a fraction less than 1% of the cost of these frontier models. Our results highlight the effectiveness of specialization and calibrated abstention in the important domain of tabular data. Auto-Fill is publicly available at https://github.com/lyrain2001/auto-fill.