aiqbench analysis
This research introduces Auto-Fill, a specialized framework that combines world knowledge, text reasoning, and code execution to accurately predict missing values in tabular data. By deploying calibrated small language models (SLMs) instead of expensive frontier models like o3-pro or Gemini 3 Pro, the approach achieves superior accuracy while reducing computational costs by over 99%. The study demonstrates that strategic specialization and dynamic model selection are critical for scaling reliable AI inference on structured datasets without sacrificing precision.
Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models
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.
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 this https URL.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Databases (cs.DB)
arXiv:2607.19847 [cs.LG]
(or arXiv:2607.19847v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.19847 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 302 words
Related coverage
Probabilistic indirect models for undrained shear strength: addressing significant data missing and variability with advanced imputation and machine learning techniques
arXiv · Aug 17, 2026
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026
Datalab Introduces OmniExtractBench to Fix Bias and Opacity in Extraction Benchmarks
MarkTechPost · Oct 2, 2026