# p2-TQA: A Process-based Preference Learning Framework for Self-Improving Table Question Answering Models

arXiv: https://arxiv.org/abs/2505.17565 · HTML: https://mlsanity.com/paper/2505.17565/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 24 of 24)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://mlsanity.com/paper/2312.06585/) (2023)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation](https://mlsanity.com/paper/2310.02304/) (2023)
- [TableLlama: Towards Open Large Generalist Models for Tables](https://mlsanity.com/paper/2311.09206/) (2023)
- [HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation](https://mlsanity.com/paper/2108.06712/) (2021)
- [Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement](https://mlsanity.com/paper/2406.11176/) (2024)
- [TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios](https://mlsanity.com/paper/2403.19318/) (2024)
- [SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables](https://mlsanity.com/paper/2305.13186/) (2023)
- [ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline](https://mlsanity.com/paper/2404.02893/) (2024)
- [TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition](https://mlsanity.com/paper/2404.10150/) (2024)
- [Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards](https://mlsanity.com/paper/2404.10346/) (2024)
- [ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context](https://mlsanity.com/paper/2403.02177/) (2024)
- [FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering](https://mlsanity.com/paper/2404.18585/) (2024)
- [Rethinking Table Instruction Tuning](https://mlsanity.com/paper/2501.14693/) (2025)
- [Semi-Supervised Reward Modeling via Iterative Self-Training](https://mlsanity.com/paper/2409.06903/) (2024)
- [Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answering](https://mlsanity.com/paper/2505.14131/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Closer Look into LLMs for Table Understanding](https://mlsanity.com/paper/2603.15402/) (2026)

## Abstract (arXiv)

Table question answering (TQA) focuses on answering questions based on tabular data. Developing TQA systems targets effective interaction with tabular data for tasks such as cell retrieval and data analysis. While recent work has leveraged fine-tuning to improve TQA systems, existing approaches often under-utilize available data and neglect the potential of post-training for further gains. In this work, we introduce p2-TQA, a process-based preference learning framework for TQA post-training. p2-TQA automatically constructs process-based preference data via a table-specific pipeline, eliminating the need for manual or costly data collection. It then optimizes models through contrastive learning on the collected data. Experiments show that p2-TQA effectively improves TQA models by up to 5% on in-domain datasets and 2.4% on out-of-domain datasets with only 8,000 training instances. Furthermore, models enhanced with p2-TQA achieve competitive results against larger, more complex state-of-the-art TQA systems, while maintaining up to five times higher efficiency.