8 papers · 1 filter
HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
Xinyue Zeng, Junhong Lin, Yujun Yan +4
The reliability of Large Language Models (LLMs) in high-stakes domains such as healthcare, law, and scientific discovery is often compromised by hallucinations. These failures typi…
How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
Junhong Lin, Bing Zhang, Song Wang +4
Large language models (LLMs) continue to struggle with knowledge-intensive questions that require up-to-date information and multi-hop reasoning. Augmenting LLMs with hybrid extern…
HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations
Shuaicheng Zhang, Haohui Wang, Junhong Lin +5
Graph heterophily, where connected nodes have different labels, has attracted significant interest recently. Most existing works adopt a simplified approach - using low-pass filter…
Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs
Junhong Lin, Song Wang, Xiaojie Guo +2
Large language models (LLMs) excel at many language understanding tasks but struggle to reason over knowledge that evolves. To address this, recent work has explored augmenting LLM…
LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection
Xinyue Zeng, Haohui Wang, Junhong Lin +3
The proliferation of open-sourced Large Language Models (LLMs) and diverse downstream tasks necessitates efficient model selection, given the impracticality of fine-tuning all cand…
Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models
Junhong Lin, Xinyue Zeng, Jie Zhu +4
Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode…