How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
Paper • 2602.10210 • Published • 1
Junhong Lin
junhongmit
AI & ML interests
None yet
Organizations
None yet
upvoted a paper 3 months ago
upvoted 3
papers 11 months ago
Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning
Paper • 2505.16122 • Published • 5
Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
Paper • 2503.22166 • Published • 3
When Heterophily Meets Heterogeneity: New Graph Benchmarks and Effective Methods
Paper • 2407.10916 • Published • 1