4 papers
How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns
Haoyue Bai, Yiyou Sun, Wenjie Hu +5
Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tunin…
GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
Chunyu Wei, Wenji Hu, Xingjia Hao +5
Large Language Models (LLMs) face significant limitations when applied to large-scale graphs, struggling with context constraints and inflexible reasoning. We present GraphChain, a…
Graph Evidential Learning for Anomaly Detection
Chunyu Wei, Wenji Hu, Xingjia Hao +4
Graph anomaly detection faces significant challenges due to the scarcity of reliable anomaly-labeled datasets, driving the development of unsupervised methods. Graph autoencoders (…
Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention
Huanxuan Liao, Wen Hu, Yao Xu +3
Large Language Models (LLMs) encounter significant challenges in long-sequence inference due to computational inefficiency and redundant processing, driving interest in context com…