6 papers
A Closer Look into LLMs for Table Understanding
Jia Wang, Chuanyu Qin, Mingyu Zheng +3
Despite the success of Large Language Models (LLMs) in table understanding, their internal mechanisms remain unclear. In this paper, we conduct an empirical study on 16 LLMs, cover…
System 1&2 Synergy via Dynamic Model Interpolation
Chenxu Yang, Qingyi Si, Chong Tian +6
Training a unified language model that adapts between intuitive System 1 and deliberative System 2 remains challenging due to interference between their cognitive modes. Recent stu…
GeoThought: A Dataset for Enhancing Mathematical Geometry Reasoning in Vision-Language Models
Nannan Shi, Chuanyu Qin, Shipeng Song +1
Large language models (LLMs) have demonstrated strong reasoning capabilities in text-based mathematical problem solving; however, when adapted to visual reasoning tasks, particular…
Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives
Wei Zeng, Hengshu Zhu, Chuan Qin +8
The ongoing evolution of AI paradigms has propelled AI research into the agentic AI stage. Consequently, the focus of research has shifted from single agents and simple application…
Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation
Tingjia Shen, Hao Wang, Chuan Qin +5
Open-domain question answering (OpenQA) represents a cornerstone in natural language processing (NLP), primarily focused on extracting answers from unstructured textual data. With…
SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models
Chuan Qin, Xin Chen, Chengrui Wang +13
In recent years, the rapid advancement of Artificial Intelligence (AI) technologies, particularly Large Language Models (LLMs), has revolutionized the paradigm of scientific discov…