Lu Lin

works on

calibration 1 experience replay 1 LLM agents 1 self-evolving critic 1 step-level confidence 1 training-free methods 1

From the 1 of 7 linked papers with an AI index.

collaborators

Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation

Yurui Chang, Bochuan Cao, Lu Lin

While large language models have demonstrated exceptional performance across a wide range of tasks, they remain susceptible to hallucinations -- generating plausible yet factually…