Tanvi Dinkar
Papers
2
Total Citations
7
H-Index
2
About
Tanvi Dinkar is a researcher at the forefront of human-robot interaction and natural language processing, with a focus on making conversational AI more engaging and verifiable. Her work bridges the gap between large language models (LLMs) and embodied systems, as demonstrated in her highly cited paper "FurChat: An Embodied Conversational Agent using LLMs, Combining Open and Closed-Domain Dialogue with Facial Expressions" (2023, 4 citations). In this study, Dinkar developed a receptionist robot on the Furhat platform that seamlessly blends scripted and open-ended dialogue with expressive facial cues, showcasing how LLMs can power more natural, socially aware interactions. Beyond deployment, she tackles the critical challenge of AI safety in "ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification" (2023, 3 citations), where she identifies why standard neural network verification methods fail for NLP—a key step toward building trustworthy language models. Her contributions are especially impactful for students and researchers exploring the intersection of robotics, dialogue systems, and AI reliability, offering both practical frameworks and foundational insights into the limitations of current verification techniques.
Research Focus
Key Achievements
Top Papers
- 1
- 2