3 citations · 8 across the 7 of their papers we have counts for
6 papers · 1 filter
Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
Cheng Wang, Qin Liu, Wenxuan Zhou +1
Group Relative Policy Optimization (GRPO) has emerged as a promising approach for improving the reasoning capabilities of large language models. However, it struggles to effectivel…
DebugLM: Learning Traceable Training Data Provenance for LLMs
Wenjie Jacky Mo, Qin Liu, Xiaofei Wen +3
Large language models (LLMs) are trained through multi-stage pipelines over heterogeneous data sources, yet developers lack a principled way to pinpoint the specific data responsib…
False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize
Cheng Wang, Zeming Wei, Qin Liu +1
Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based ap…
QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA
Jacob Dineen, Aswin RRV, Qin Liu +8
Alignment of large language models (LLMs) with principles like helpfulness, honesty, and harmlessness typically relies on scalar rewards that obscure which objectives drive the tra…
Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
Terry Tong, Jiashu Xu, Qin Liu +1
Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text, expanding their dialogue capabilities beyond a single uttera…
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
Wenjie Mo, Jiashu Xu, Qin Liu +5
Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the c…