Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models
Yurong Liu, Yeye He, Haoyu Dong, Junjie Xing, Shi Han, Dongmei Zhang, Surajit Chaudhuri
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Self-Consistency Improves Chain of Thought Reasoning in Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
Builds on26
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Gradient Surgery for Multi-Task LearningTianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine et al.NeurIPS 2020 · 2,261 citations
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMsMiao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li et al.ICLR 2024 · 867 citations
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
- Dataset Discovery in Data LakesAlex Bogatu, Alvaro A. A. Fernandes, Norman W. Paton, Nikolaos KonstantinouICDE 2020 · 118 citations
Related papers
- Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RLHaotian Zhai, Jingcheng Liang, Dongyeop KangACL Findings 2026 · 1 citation
- Getting MoRE out of Mixture of Language Model Reasoning ExpertsChenglei Si, Weijia Shi, Chen Zhao, Luke Zettlemoyer et al.EMNLP Findings 2023 · 9 citations
- Generalization or Memorization? Multi-Agent vs. Baseline LLMs and AutoML Models for Tabular ClassificationAida Sanatizadeh, Sorouralsadat Fatemi, Reza Mousavi, Ahmed AbbasiACL Findings 2026
- Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table UnderstandingYuhang Zhou, Mingrui Zhang, Ke Li, Mingyi Wang et al.ACL 2026 · 5 citations
- Specializing Smaller Language Models towards Multi-Step ReasoningYao Fu, Hao Peng, Litu Ou, Ashish Sabharwal et al.ICML 2023 · 347 citations
