paper-with-me

홈 › Papers

TableReasoner: Advancing Table Reasoning Framework with Large Language Models

2025-07-10 · Sishi Xiong, Dakai Wang, Yu Zhao, Jie Zhang, Changzai Pan, Haowei He, Xiangyu Li, Wenhan Chang, Zhongjiang He, Shuangyong Song, Yongxiang Li arxiv

The paper presents our system developed for table question answering (TQA). TQA tasks face challenges due to the characteristics of real-world tabular data, such as large size, incomplete column semantics, and entity ambiguity. To address these issues, we propose a large language model (LLM)-powered and programming-based table reasoning framework, named TableReasoner. It models a table using the schema that combines structural and semantic representations, enabling holistic understanding and efficient processing of large tables. We design a multi-step schema linking plan to derive a focused table schema that retains only query-relevant information, eliminating ambiguity and alleviating hallucinations. This focused table schema provides precise and sufficient table details for query refinement and programming. Furthermore, we integrate the reasoning workflow into an iterative thinking architecture, allowing incremental cycles of thinking, reasoning and reflection. Our system achieves first place in both subtasks of SemEval-2025 Task 8.

📄 PDF Abstract BibTeX arXiv:2507.08046

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision

2025-10-19 · Kanghui Ning, Zijie Pan, Yushan Jiang, Anderson Schneider 외 arxiv

Time series reasoning is emerging as the next frontier in temporal analysis, aiming to move beyond pattern recognition towards explicit, interpretable, and trustworthy inference. This paper presents a BlueSky vision buil…

PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning

2026-01-21 · Yao Lu, Dengdong Fan, Jianzheng Nie, Fan Xu 외 arxiv

We present PCL-Reasoner-V1.5, a 32-billion-parameter large language model (LLM) for mathematical reasoning. The model is built upon Qwen2.5-32B and refined via supervised fine-tuning (SFT) followed by reinforcement learn…

Reinforcement LearningMathematical ReasoningOffline RL

MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs

2025-08-04 · Guojiang Zhao, Zixiang Lu, Yutang Ge, Sihang Li 외 arxiv

Large Language Models (LLMs) have shown impressive performance across various domains, but their ability to perform molecular reasoning remains underexplored. Existing methods mostly rely on general-purpose prompting, wh…

Can GRPO Boost Complex Multimodal Table Understanding?

2025-09-21 · Xiaoqiang Kang, Shengen Wu, Zimu Wang, Yilin Liu 외 arxiv

Existing table understanding methods face challenges due to complex table structures and intricate logical reasoning. While supervised finetuning (SFT) dominates existing research, reinforcement learning (RL), such as Gr…

Reinforcement LearningLogical Reasoning

DART: Difficulty-Adaptive Reasoning Truncation for Efficient Large Language Models

2025-11-03 · Ruofan Zhang, Bin Xia, Zhen Cheng, Cairen Jian 외 arxiv

Adaptive reasoning is essential for aligning the computational effort of large language models (LLMs) with the intrinsic difficulty of problems. Current chain-of-thought methods boost reasoning ability but indiscriminate…

Reinforcement Learning