mlsanityData to 7 Oct 2026

ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context

arXiv 2403.02177 ↗First posted 4 Mar 2024cs.CLcited by 23

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Tables play a crucial role in conveying information in various domains. We propose a Plan-then-Reason framework to answer different types of user queries over tables with sentence context. The framework first plans the reasoning paths over the context, then assigns each step to program-based or textual reasoning to reach the final answer. This framework enhances the table reasoning abilities for both in-context learning and fine-tuning methods. GPT-3.5-Turbo following Plan-then-Reason framework surpasses other prompting baselines without self-consistency while using less API calls and in-context demonstrations. We also construct an instruction tuning set TrixInstruct to evaluate the effectiveness of fine-tuning with this framework. We present ProTrix model family by finetuning models on TrixInstruct. Our experiments show that ProTrix family generalizes to diverse unseen tabular tasks with only 6k training instances. We further demonstrate that ProTrix can generate accurate and faithful explanations to answer complex free-form questions. Our work underscores the importance of the planning and reasoning abilities towards a model over tabular tasks with generalizability and interpretability. We open-source our dataset and models at https://github.com/WilliamZR/ProTrix.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 36 of its 61 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

36 of 61 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding9 Jan
  2. 2023SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables22 May
  3. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning31 Jan
  4. 2022Large Language Models are few(1)-shot Table Reasoners13 Oct
  5. 2022TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data25 May

Other references · 31

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  5. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  6. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  7. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  8. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  9. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  10. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  11. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  12. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
19 more
  1. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
  2. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  3. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  4. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  5. 2022Binding Language Models in Symbolic Languagescited by 224
  6. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  7. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 166
  8. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
  9. 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
  10. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  11. 2022TableFormer: Robust Transformer Modeling for Table-Text Encodingcited by 90
  12. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  13. 2023Table-GPT: Table-tuned GPT for Diverse Table Taskscited by 69
  14. 2020On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queriescited by 59
  15. 2022PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-trainingcited by 41
  16. 2024StructLM: Towards Building Generalist Models for Structured Knowledge Groundingcited by 29
  17. 2023S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answeringcited by 17
  18. 2023From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuningcited by 14
  19. 2022APOLLO: An Optimized Training Approach for Long-form Numerical Reasoningcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 12; 2026: 4.

23 papers.

Sort:

By area:

  1. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  2. 2025Table-R1: Region-based Reinforcement Learning for Table Understandingcited by 35
  3. 2024Interpretable LLM-based Table Question Answeringcited by 18
  4. 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answeringcited by 13
  5. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoningcited by 10
  6. 2025RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversalscited by 10
  7. 2025When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tablescited by 10
  8. 2024FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formatscited by 8
  9. 2025Weaver: Interweaving SQL and LLM for Table Reasoningcited by 8
  10. 2026Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Searchcited by 8
  11. 2025Table as a Modality for Large Language Modelscited by 7
  12. 2024TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarizationcited by 6
11 more
  1. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 4
  2. 2024TabVer: Tabular Fact Verification with Natural Logiccited by 3
  3. 20242D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Modelscited by 2
  4. 2025LLM Inference Enhanced by External Knowledge: A Surveycited by 2
  5. 2025Utilizing Training Data to Improve LLM Reasoning for Tabular Understandingcited by 2
  6. 2025p2-TQA: A Process-based Preference Learning Framework for Self-Improving Table Question Answering Modelscited by 1
  7. 2025ExpliCIT-QA: Explainable Code-Based Image Table Question Answeringcited by 1
  8. 2025RUST-BENCH: Benchmarking LLM Reasoning on Unstructured Text within Structured Tablescited by 1
  9. 2026Analyzing LLM Instruction Optimization for Tabular Fact Verificationcited by 1
  10. 2026A Multi-Agent Approach for Claim Verification from Tabular Data Documentscited by 0
  11. 2026Discovery-Driven Integration of Disjoint Tables via Textcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing Table Reasoning with Deterministic Table-State Rewards
  2. 2025Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
  3. 2022ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples
  4. 2025No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning
  5. 2025STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models
  6. 2026TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering
  7. 2026Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering
  8. 2026Beyond Linearization: Attributed Table Graphs for Table Reasoning