Abhilekh Borah / অভিলেখ বৰা
making llms more human 🌻
Update: I will be joining Microsoft Research, India as a Research Intern this Spring (March 2026).
Hey! I'm Abhilekh Borah, a final-year CS undergraduate at
Manipal University Jaipur, India. My prime interest lies in AI Alignment,
exploring how large language and vision models can operate
safely, ethically and responsibly that reflect
human values, behavior, and user intent,
contributing to more equitable, trustworthy, and fair systems.
I have first-authored 8+ research papers at top-tier core CS conferences such as ICLR, ACL, EMNLP, AAAI, and EACL. In addition, I have conducted research across both academia and industry through 6+ internships at organizations such as Adobe (Media & Data Science Research Lab), and the National University of Singapore (Centre for Trusted Internet Community).
Please check out publications for more details about my work. If you’re interested in discussing research or exploring collaborations, feel free to reach out at abhilekhxborah@gmail.com.
News 🔥
🎉 ObfusQAte has been accepted at LREC 2026!
🎉 Social Agents has been accepted at ICLR 2026!
🎉 Don't Judge a Book by its Cover has been selected for an Oral presentation at EACL 2026!
🇸🇬 Presented two of our papers, DETONATE (Oral) and Always Refuse, at AAAI 2026 in Singapore.
🇮🇳 Presented our paper, The Visual Counter Turing Test, at IJCNLP-AACL 2025 in Mumbai, India.
🇨🇳 Presented two of our papers, Alignment Quality Index (Oral) and DRISHIKON, at EMNLP 2025 in Suzhou, China.
🏆 CliME has been awarded the Outstanding Paper Award at ACL 2025, NLP for Positive Impact Workshop, in Vienna, Austria 🇦🇹.