256 citations · 280 across the 16 of their papers we have counts for
9 papers · 1 filter
MetaScale: Test-Time Scaling with Evolving Meta-Thoughts
Qin Liu, Wenxuan Zhou, Nan Xu +5
One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively sel…
Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
Qin Liu, Chao Shang, Ling Liu +7
The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phen…
SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
Qin Liu, Fei Wang, Chaowei Xiao +1
Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of the large language model (LLM) parametric knowledge with non-preferred features is unifo…
Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
Dongwon Jung, Qin Liu, Tenghao Huang +2
Retrieval-augmented generation (RAG) improves large language models (LMs) by incorporating non-parametric knowledge through evidence retrieved from external sources. However, it of…
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
Jiangshu Du, Yibo Wang, Wenting Zhao +37
This work is motivated by two key trends. On one hand, large language models (LLMs) have shown remarkable versatility in various generative tasks such as writing, drawing, and ques…
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors
Victoria Graf, Qin Liu, Muhao Chen
Data poisoning backdoor attacks can cause undesirable behaviors in large language models (LLMs), and defending against them is of increasing importance. Existing defense mechanisms…