Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Tharindu Kumarage

Tharindu Kumarage

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Crypto×1ML×1

Frequent co-authors

Charith Peris2×
Rahul Gupta2×
Swastik Roy1×
Rajkumar Pujari1×
Anna Rumshisky1×
Pradeep Natarajan1×

Research Timeline

2026
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial prompts, leading to enhanced safety robustness.

PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges

PReMISE introduces a framework to audit and improve the quality of rubrics used to guide LLM judges, demonstrating that it can significantly increase judge accuracy and reduce the exploitability of responses.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 29, 2026

PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges

Swastik Roy, Rajkumar Pujari, Tharindu Kumarage, Charith Peris +4 more

PReMISE introduces a framework to audit and improve the quality of rubrics used to guide LLM judges, demonstrating that it can significantly increase judge accuracy and reduce the exploitability of re…

View →
cs.AIcs.CRcs.LGRecentApr 20, 2026

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System

Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna +4 more

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial…

View →