Papers by Geng Hong

GenGO

Omakase Read Later

Search

Papers by Geng Hong

ACL

2026.acl-long

reasoning process
internal attention mechanisms
LRM
scaling sampling strategy
reasoning process of LRMs
inference cost
reasoning-intensive tasks
content generation
safety-oriented reflections
decoding

2026

Reasoning

1 papers

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments (2026.acl-long)

Copied to clipboard

Yuquan Wang, Mi Zhang, Yining Wang, Geng Hong, Mi Wen, Xiaoyu You, Min Yang

Challenge:	Existing defenses for Large Reasoning Models (LRMs) depend on costly fine-tuning and additional expert knowledge, which limits their scalability.
Approach:	They propose an inference-time safeguard for Large Reasoning Models that injects safety aha moments into the reasoning process to guide the model towards harmless yet helpful reasoning.
Outcome:	The proposed safeguard outperforms nine existing safeguards while avoiding common exaggerated safety issues.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations