Papers by Tharindu Kumarage
Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey (2024.naacl-long)
Copied to clipboard
| Challenge: | Increasing the use of knowledge graphs to augment LLMs has led to hallucinations . large language models (LLMs) are prone to producing hallucinosis due to knowledge gaps . |
| Approach: | They review knowledge graph-based augmentation techniques in large language models to assess their effectiveness and examine their performance. |
| Outcome: | The proposed methods have been evaluated against three groups of LLMs and offer methodological comparisons and performance evaluations. |
How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to detect AI-generated text are inadequate, causing misuse of the text. |
| Approach: | They propose a universal evasive prompt framework that can prompt any PLM to generate “human-like” text that can mislead detectors. |
| Outcome: | The proposed approach can prompt any PLM to generate “human-like” text that can mislead detectors. |
Defending Against Social Engineering Attacks in the Age of LLMs (2024.emnlp-main)
Copied to clipboard
Lin Ai, Tharindu Kumarage, Amrita Bhattacharjee, Zizhou Liu, Zheng Hui, Michael Davinroy, James Cook, Laura Cassani, Kirill Trapeznikov, Matthias Kirchner, Arslan Basharat, Anthony Hoogs, Joshua Garland, Huan Liu, Julia Hirschberg
| Challenge: | Existing research has developed frameworks to understand human-to-human CSE attacks. |
| Approach: | They propose a modular defense pipeline that improves detection at both the message and conversation levels. |
| Outcome: | The proposed model can be exploited to facilitate chat-based social engineering attacks and generate high-quality CSE content, but their detection capabilities are suboptimal, leading to increased operational costs for defense. |
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System (2026.acl-long)
Copied to clipboard
Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Aram Galstyan, Charith Peris
| Challenge: | Existing red-teaming approaches focus on policy-level weaknesses, but they overlook systemic weaknesses . aRES exploits dual-targeting weaknesses in both the core LLM and the RM simultaneously. |
| Approach: | a new framework uncovers weaknesses in both the core and the reward models simultaneously . a "Safety Mentor" generates semantically coherent adversarial prompts . |
| Outcome: | ARES uncovers weaknesses in both the core LLM and the RM simultaneously . it fine-tunes the LM to detect harmful content, then optimizes the core model . |
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation (2025.findings-acl)
Copied to clipboard
Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna, Xinyan Zhao, Richard Zemel, Kai-Wei Chang, Aram Galstyan, Rahul Gupta, Charith Peris
| Challenge: | Safety reasoning paradigms require high-quality policy-embedded chain-of-thought datasets . generating such data through human annotations is prohibitively expensive . |
| Approach: | They propose AIDSAFE: Agentic Iterative Deliberation for Safety Reasoning . AIDS AFE leverages multi-agent deliberation to iteratively expand reasoning on safety policies . |
| Outcome: | The proposed model improves policy adherence and reasoning quality while maintaining acceptable utility and over-refusal accuracy. |