Computer science researcher codes compassionate AI

In 2020, Snigdha Chaturvedi joined the faculty at Carolina, where she is an associate professor in the UNC College of Arts and Sciences’ computer science department. Chaturvedi has been a major contributor to conversations about ethics and education in artificial intelligence.

“I get to do what I’m passionate about, but at the same time, I’m in close contact with other people who are doing related research, which is an incredible resource,” Chaturvedi says.

Chaturvedi’s research focuses on how natural language processing and large language models can understand and respond to human communication with more social awareness.

Natural language processing is a branch of AI that trains machines to understand and interact with human language. Think of it as teaching a computer to read and understand a book — deciphering words, sentences and their meanings. Large language models are some of the most advanced tools in natural language processing.

These models are trained on vast amounts of text, which they then learn from to generate responses. The better the data fed to the system and the better the training procedure, the more human-like and accurate its response. If data with bias, inaccuracies or misinformation is used to teach the system, that will lead to biased outputs or nonsensical responses.

“Humans are so natural with language,” Chaturvedi explains. “Even a 2-year-old can understand language and to some extent speak. But language is just so challenging for machines.”

These models struggle to grasp the social context, emotions and deeper meanings behind language. And Chaturvedi is determined to find ways to make the technology more empathetic and in tune with how humans interact — a strategy she hopes will diminish the social bias that these machines sometimes exhibit.

In 2024, Chaturvedi created SocialGaze, a framework designed to guide a language model through a thoughtful, multistep process in which it examines a social scenario from different people’s feelings, attitudes and actions. She found that when prompted to analyze multiple perspectives, large language models were more aligned with human judgments.

“There are so many implications of a word, and not just linguistic implications, but also social and pragmatic implications,” she says. “So it’s very important to explore these possibilities.”

Advocating for compassionate technology

When thinking about the potential impact of her research, Chaturvedi envisions a world where AI agents can provide support in areas where people lack access to essential services like therapy or health care.

“I come from a conservative society in India where people don’t have access to those facilities,” she says. “Or if they have access, there’s just so much social stigma associated with seeking help that people would rather suffer their entire life than make an appointment.”

Read more about AI resources at Carolina.

In these cases, having AI agents that understand the subtle complexities of human communication is critical to providing thoughtful responses that relate to specific human experiences.

“Imagine the potential of an AI agent with deeper social understanding,” she suggests. “If somebody is stressed, they can just take out their phone and chat with someone — an AI agent. I think that’s a very powerful use case.”

These models can excel at routine tasks like transcribing notes and analyzing data, freeing up professionals to focus on more complex and personal interactions with patients or clients. Chaturvedi also believes AI can act as a “co-expert,” quickly processing data and identifying patterns that might take humans hours to find, enhancing the quality of care.

“The recent progress in NLP has been very invigorating because I see that my research is now being used for so many people in day-to-day life,” she says.

Read more about Chaturvedi’s AI research.