5 papers
Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models
Zhanke Zhou, Zhaocheng Zhu, Xuan Li +5
Numerous applications of large language models (LLMs) rely on their ability to perform step-by-step reasoning. However, the reasoning behavior of LLMs remains poorly understood, po…
Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention
Zhihao Zhan, Jianan Zhao, Zhaocheng Zhu +1
Efficient long-context modeling remains a critical challenge for natural language processing (NLP), as the time complexity of the predominant Transformer architecture scales quadra…
From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
Zhanke Zhou, Xiao Feng, Zhaocheng Zhu +3
While existing benchmarks probe the reasoning abilities of large language models (LLMs) across diverse domains, they predominantly assess passive reasoning, providing models with a…
Fully-inductive Node Classification on Arbitrary Graphs
Jianan Zhao, Zhaocheng Zhu, Mikhail Galkin +3
One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new struct…
Large Language Models can Learn Rules
Zhaocheng Zhu, Yuan Xue, Xinyun Chen +4
When prompted with a few examples and intermediate steps, large language models (LLMs) have demonstrated impressive performance in various reasoning tasks. However, prompting metho…