most citedAnchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL2026

From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs

Yanrui Du, Yibo Gao, Sendong Zhao +6

R1-style LLMs have attracted growing attention for their capacity for self-reflection, yet the internal mechanisms underlying such behavior remain unclear. To bridge this gap, we a…

cs.LG2026

medR: Reward Engineering for Clinical Offline Reinforcement Learning via Tri-Drive Potential Functions

Qianyi Xu, Gousia Habib, Feng Wu +5

Reinforcement Learning (RL) offers a powerful framework for optimizing dynamic treatment regimes (DTRs). However, clinical RL is fundamentally bottlenecked by reward engineering: t…

cs.CL2026

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs

Yanrui Du, Sendong Zhao, Yibo Gao +9

Large language models (LLMs) equipped with chain-of-thought (CoT) achieve strong performance and offer a window into LLM behavior. However, recent evidence suggests that improvemen…

cs.AI2026

OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation

Yi Jiang, Sendong Zhao, Jianbo Li +4

Retrieval-Augmented Generation (RAG) improves generation quality by incorporating evidence retrieved from large external corpora. However, most existing methods rely on statically…

cs.CL2025

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security

Yanrui Du, Fenglei Fan, Sendong Zhao +3

As Large Language Models (LLMs) increasingly permeate human life, their security has emerged as a critical concern, particularly their ability to maintain harmless responses to mal…

cs.CL20251 cited

Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint

Yanrui Du, Fenglei Fan, Sendong Zhao +6

Instruction Fine-Tuning (IFT) has been widely adopted as an effective post-training strategy to enhance various abilities of Large Language Models (LLMs). However, prior studies ha…