Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation
Sy-Tuyen Ho, Minghui Liu, Furong Huang +1
LLMs increasingly assist scientific peer review. This creates a feedback loop when generated reviews enter the training data of future LLMs. While recursive training has been studi…
cs.LG2026
Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model
Pankayaraj Pathmanathan, Furong Huang
While the wide adoption of refusal training in large language models (LLMs) has showcased improvements in model safety, recent works have highlighted shortcomings due to the shallo…