Tharindu Kumarage — accepted AI-conference papers

2025

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation

Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna, Xinyan Zhao, Richard Zemel, Kai-Wei Chang +3

ACL 2025finding

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-refusal and jailbreak vulnerabilities. However, implementing this paradigm is challenging due to the resource-intensive pr…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey

Garima Agrawal, Tharindu Kumarage, Zeyad Alghamdi, Huan Liu

NAACL 2024long

The contemporary LLMs are prone to producing hallucinations, stemming mainly from the knowledge gaps within the models. To address this critical limitation, researchers employ diverse strategies to augment the LLMs by incorporating external knowledge, aiming to reduce hallucinations and enhance reas…

Cited by 125 Source ↗PDF ↗Scholar ↗