1 citations · 1 across the 2 of their papers we have counts for
3 papers · 1 filter
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
Jiacheng Liang, Yao Ma, Tharindu Kumarage +5
Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an imperfect Reward Model (RM) ca…
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation
Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna +6
Safety reasoning is a recent paradigm where LLMs reason over safety policies before generating responses, thereby mitigating limitations in existing safety measures such as over-re…
CyberBOT: Towards Reliable Cybersecurity Education via Ontology-Grounded Retrieval Augmented Generation
Chengshuai Zhao, Riccardo De Maria, Tharindu Kumarage +7
Advancements in large language models (LLMs) have enabled the development of intelligent educational tools that support inquiry-based learning across technical domains. In cybersec…