6 papers
Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
Xinyu Yuan, Xixian Liu, Jianan Zhao +3
Perturbation experiments are central to understanding cellular mechanisms, but remain costly and sparse, motivating prediction of gene expression responses for unobserved condition…
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…
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…
A Foundation Model for Zero-shot Logical Query Reasoning
Mikhail Galkin, Jincheng Zhou, Bruno Ribeiro +2
Complex logical query answering (CLQA) in knowledge graphs (KGs) goes beyond simple KG completion and aims at answering compositional queries comprised of multiple projections and…