Ongoing Projects

Structured Narrative Processing and Generation

Current researchers: Patty Delafuente, Krish Mehta

Although I have worked on neurosymbolic automated story generation for a while, I believe neurosymbolic techniques are becoming even more important in today’s era of large language modeling. Symbolic techniques are older AI techniques that often involve a significant amount of hand engineering but can result in predictable & interpretable output and behavior. These can range from rule-based systems to planners. Neurosymbolic storytelling enables systems to have the flexibility and broad range of output that LLMs can generate while maintaining important storytelling components such as plot, coherency, and consistency. We are also looking at narrative as a mode of communication within robotics and detecting inconsistencies in data.

Related Papers from the Lab

• CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding (2023)

• CIS²: A Simplified Commonsense Inference Evaluation for Story Prose (2022)

• Event Representations for Automated Story Generation with Deep Neural Nets (2018)

AI Agents for Playing Dungeons and Dragons

Current researchers: Thanya Balamurugan, Arya Honraopatil

Dungeons & Dragons (D&D) is a tabletop roleplaying game originally created in the 1970s. Now that we’ve seen AI that can play games like Go, DotA 2, or Diplomacy, I believe D&D is the next big challenge in AI. The game lends itself to a variety of interesting problems where players have to use skills in Theory of Mind and improvisational storytelling, all while following the rules of the game.

Related Papers from the Lab

• Does Reasoning Help LLM Agents Play Dungeons and Dragons? A Prompt Engineering Experiment (2025)

• CALYPSO: LLMs as Dungeon Masters’ Assistants (2023)

• FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information (2023)

• Dungeons and Dragons as a Dialogue Challenge for Artificial Intelligence (2022)

• Dungeons and DQNs: Toward Reinforcement Learning Agents that Play Tabletop Roleplaying Games (2018)

Customizable Assistive Technologies

Current researchers: Shadab Choudhury, Marcus McAllister

The majority of this work revolves around Augmentative and Alternative Communication (AAC). AAC tools have been largely ignored by the natural language processing community. However, even though it has been an exciting time in AI, we must implement such tools with caution – taking into consideration what AAC users actually want. I am interested in improving AAC by adding in various natural language processing techniques without sacrificing users’ autonomy, privacy, or personality.

Related Papers from the Lab

• Evaluating Human-LLM Representation Alignment: A Case Study on Affective Sentence Generation for Augmentative and Alternative Communication (2025)

• Aging Up AAC: An Introspection on Augmentative and Alternative Communication Applications for Autistic Adults (2024)

Customizable and Emotive Speech Synthesis

Current researchers: Shadab Choudhury, Arya Honraopatil, Padina Nasiri Toussi

Now that transformer models have greatly improved speech synthesis (also called text-to-speech/TTS) capabilities, I believe the next step is to make voices that can emulate the rich tapestry of people’s voice qualities.

Related Papers from the Lab

Debugging Tools for Code Generation

Current researchers: Sara Abbas, Maria Antonette Vanya

This is a side project looking at creating debugging tools for coders without diminishing their involvement in the process.

Related Papers from the Lab