TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction

• URL: http://arxiv.org/abs/2602.11700v1
• Date: Thu, 12 Feb 2026 08:28:58 GMT
• Title: TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction
• Authors: Yongyao Wang, Ziqi Miao, Lu Yang, Haonan Jia, Wenting Yan, Chen Qian, Lijun Li,
• Abstract summary: We propose TabSieve, a select-then-predict framework that makes evidence usage explicit and auditable.<n>Given a table and a query row, TabSieve first selects a small set of informative rows as evidence and then predicts the missing target conditioned on the selected evidence.<n>Experiments on a held-out benchmark of 75 classification and 52 regression tables show that TabSieve consistently improves performance across shot budgets.
• Score: 14.270578219134997
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tabular prediction can benefit from in-table rows as few-shot evidence, yet existing tabular models typically perform instance-wise inference and LLM-based prompting is often brittle. Models do not consistently leverage relevant rows, and noisy context can degrade performance. To address this challenge, we propose TabSieve, a select-then-predict framework that makes evidence usage explicit and auditable. Given a table and a query row, TabSieve first selects a small set of informative rows as evidence and then predicts the missing target conditioned on the selected evidence. To enable this capability, we construct TabSieve-SFT-40K by synthesizing high-quality reasoning trajectories from 331 real tables using a strong teacher model with strict filtering. Furthermore, we introduce TAB-GRPO, a reinforcement learning recipe that jointly optimizes evidence selection and prediction correctness with separate rewards, and stabilizes mixed regression and classification training via dynamic task-advantage balancing. Experiments on a held-out benchmark of 75 classification and 52 regression tables show that TabSieve consistently improves performance across shot budgets, with average gains of 2.92% on classification and 4.45% on regression over the second-best baseline. Further analysis indicates that TabSieve concentrates more attention on the selected evidence, which improves robustness to noisy context.

Related papers

• Explicit Uncertainty Modeling for Active CLIP Adaptation with Dual Prompt Tuning [51.99383151474742]
  We propose a robust uncertainty modeling framework for active CLIP adaptation based on dual-prompt tuning.<n>We show that our method consistently outperforms existing active learning methods under the same annotation budget.
  arXiv  Detail & Related papers  (2026-02-04T09:01:55Z)
• Enhancing TableQA through Verifiable Reasoning Trace Reward [38.96476258377461]
  We introduce RE-Tab, a plug-and-play framework that architecturally enhances trajectory search via lightweight, training-free reward modeling.<n>We demonstrate that providing explicit verifiable rewards during State Transition (What is the best action?'') and Simulative Reasoning (Am I sure about the output?'') is crucial to steer the agent's navigation in table states.<n>A direct plug-and-play implementation of RE-Tab brings up to 41.77% improvement in QA accuracy and 33.33% drop in test-time inference samples for consistent answer.
  arXiv  Detail & Related papers  (2026-01-30T04:06:42Z)
• CORE-T: COherent REtrieval of Tables for Text-to-SQL [91.76918495375384]
  CORE-T is a scalable, training-free framework that enriches tables with purpose metadata and pre-computes a lightweight table-compatibility cache.<n>Across Bird, Spider, and MMQA, CORE-T improves table-selection F1 by up to 22.7 points while retrieving up to 42% fewer tables.
  arXiv  Detail & Related papers  (2026-01-19T14:51:23Z)
• TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning [77.01182934427095]
  TaTToo is a novel table-grounded PRM framework that integrates tool-based verification to provide precise reward supervision.<n>We train TaTToo with a dual-stage paradigm: cold-start supervised fine-tuning to capture tool-use reasoning patterns, followed by reinforcement learning to align our model with table-based verification.
  arXiv  Detail & Related papers  (2025-10-07T17:59:41Z)
• Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning [24.624844234355734]
  Reasoning-Table is the first application of reinforcement learning (RL) to table reasoning, achieving state-of-the-art performance.<n> Reasoning-Table emerges as a robust table reasoning large language model, surpassing larger proprietary models like Claude-3.7-Sonnet by 4.0%.
  arXiv  Detail & Related papers  (2025-06-02T14:18:09Z)
• Towards Fair In-Context Learning with Tabular Foundation Models [6.4989916051093815]
  We present the first investigation of fairness in Transformer-based in-context learning (ICL)<n>We evaluate three recently proposed foundation models -- TabPFNv2, TabICL, and TabDPT -- on benchmark datasets.<n>Our experiments show that the uncertainty-based strategy consistently improves group fairness metrics with minimal impact on predictive accuracy.
  arXiv  Detail & Related papers  (2025-05-14T15:53:14Z)
• The Mighty ToRR: A Benchmark for Table Reasoning and Robustness [45.420943398134845]
  ToRR is a benchmark for Table Reasoning and Robustness, measuring model performance and robustness on table-related tasks.<n>We present a leaderboard as well as comprehensive analyses of the results of leading models over ToRR.
  arXiv  Detail & Related papers  (2025-02-26T18:56:38Z)
• FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formats [48.47559543509975]
  We propose FLEXTAF-Single and FLEXTAF-Vote to enhance table reasoning performance by employing flexible formats. Our experiments on WikiTableQuestions and TabFact reveal significant improvements, with average gains of 2.3% and 4.8%.
  arXiv  Detail & Related papers  (2024-08-16T17:00:11Z)
• KET-QA: A Dataset for Knowledge Enhanced Table Question Answering [63.56707527868466]
  We propose to use a knowledge base (KB) as the external knowledge source for TableQA. Every question requires the integration of information from both the table and the sub-graph to be answered. We design a retriever-reasoner structured pipeline model to extract pertinent information from the vast knowledge sub-graph.
  arXiv  Detail & Related papers  (2024-05-13T18:26:32Z)
• Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding [79.9461269253121]
  We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts. Chain-of-Table achieves new state-of-the-art performance on WikiTQ, FeTaQA, and TabFact benchmarks.
  arXiv  Detail & Related papers  (2024-01-09T07:46:26Z)
• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [55.33939289989238]
  We propose TAP4LLM as a versatile pre-processor suite for leveraging large language models (LLMs) in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding.
  arXiv  Detail & Related papers  (2023-12-14T15:37:04Z)
• TabPert: An Effective Platform for Tabular Perturbation [6.555691728969102]
  TabPert allows a user to update a table, change its associated hypotheses, change their labels, and highlight rows that are important for hypothesis classification. These counterfactual tables and hypotheses, as well as the metadata, can then be used to explore an existing model's shortcomings methodically and quantitatively.
  arXiv  Detail & Related papers  (2021-08-02T02:37:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.