7 papers
Controlling Tool Use with Heading-Specific Activation Steering
Yuqi Chen, Vincent Siu, Yang Liu +2
Tool-augmented large language models extend their capabilities beyond parametric knowledge through external tools, but tend to invoke them unnecessarily. We investigate whether too…
CTIConnect: A Benchmark for Retrieval-Augmented LLMs over Heterogeneous Cyber Threat Intelligence
Yutong Cheng, Yang Liu, Changze Li +2
Cyber Threat Intelligence (CTI) is foundational to modern cybersecurity, enabling organizations to proactively defend against evolving threats. However, the sheer volume and hetero…
Reducing Detail Hallucinations in Long-Context Regulatory Understanding via Targeted Preference Optimization
Yang Liu, Bin Chong, Yuhan Lin +7
Large language models (LLMs) frequently produce \emph{detail hallucinations} when processing long regulatory documents, including subtle errors in threshold values, units, scopes,…
RepIt: Steering Language Models with Concept-Specific Refusal Vectors
Vincent Siu, Nathan W. Henry, Nicholas Crispino +3
Current safety evaluations of language models rely on benchmark-based assessments that may miss localized vulnerabilities. We present RepIt, a simple and data-efficient framework f…
RADIANT-LLM: an Agentic Retrieval Augmented Generation Framework for Reliable Decision Support in Safety-Critical Nuclear Engineering
Zavier Ndum Ndum, Jian Tao, John Ford +2
Reliable decision support in nuclear engineering requires traceable, domain-grounded knowledge retrieval, yet safety and risk analysis workflows remain hampered by fragmented docum…
SteeringSafety: Benchmarking Representation Steering in LLMs Across Safety Perspectives
Vincent Siu, Nicholas Crispino, David Park +5
We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets. While prior work highlights the genera…