15 papers
Test Time Training for Supervised Causal Learning
Zizhen Deng, Jiaru Zhang, Rui Ding +5
Supervised Causal Learning (SCL) has shown promise in causal discovery by framing it as a supervised learning problem. However, it suffers from significant out-of-distribution gene…
CAST: Achieving Stable LLM-based Text Analysis for Data Analytics
Jinxiang Xie, Zihao Li, Wei He +3
Text analysis of tabular data relies on two core operations: \emph{summarization} for corpus-level theme extraction and \emph{tagging} for row-level labeling. A critical limitation…
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
Hanbing Liu, Lang Cao, Yuanyi Ren +5
Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been…
Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning
Lang Cao, Jingxian Xu, Hanbing Liu +5
Tables are a fundamental medium for organizing and analyzing data, making table reasoning a critical capability for intelligent systems. Although large language models (LLMs) exhib…
MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark
Junjie Xing, Yeye He, Mengyu Zhou +6
Tables and table-based use cases play a crucial role in many important real-world applications, such as spreadsheets, databases, and computational notebooks, which traditionally re…
TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance
Jingxian Xu, Mengyu Zhou, Weichang Liu +3
Large Language Models (LLMs) have made significant strides in problem-solving by incorporating reasoning processes. However, this enhanced reasoning capability results in an increa…