LLMGuard: Guarding Against Unsafe LLM Behavior
- Shubh Goyal
- Medha Hira
- et al.
- 2024
- AAAI 2024
I work as an Advisory Research Scientist at IBM Research India. I primarily work on Data for AI, Fairness and Algorithmic Bias. I am passionate about building algorithms for controlled text generation. My job responsibility includes designing and developing NLP and Machine Learning based solutions for businesses. I have also been leading multiple academic research collaborations and have mentored ~30+ students. My work has been covered by leading newspapers, blogs and also featured in MIT Technology Review. I have co-authored several research papers published in renowned computer science journals and conferences. I have delivered many talks and guest lectures at national and international venues like IIITD, VIT Amravati, Northcap University, DTU Delhi, EPFL Switzerland, GHCI Bangalore, FES Berlin, NUS Singapore etc.
For any questions/ concerns, write to me at nishthamadaan@in.ibm.com.
You can visit my Linkedin profile for more details - https://www.linkedin.com/in/nishtha-madaan-21017541/