4 papers
LLMs and their Limited Theory of Mind: Evaluating Mental State Annotations in Situated Dialogue
Katharine Kowalyshyn, Matthias Scheutz
What if large language models could not only infer human mindsets but also expose every blind spot in team dialogue such as discrepancies in the team members' joint understanding?…
Belief or Circuitry? Causal Evidence for In-Context Graph Learning
Katharine Kowalyshyn, Timothy Duggan, Daniel Little +1
How do LLMs learn in-context? Is it by pattern-matching recent tokens, or by inferring latent structure? We probe this question using a toy graph random-walk across two competing g…
Are you with me? A Framework for Detecting Mental Model Discrepancies in Task-Based Team Dialogues
Katharine Kowalyshyn, Matthias Scheutz
Humans typically use natural language to update teammates on task states. Since not all updates are communicated, discrepancies arise between the team members' mental models that n…
IntelliProof: An Argumentation Network-based Conversational Helper for Organized Reflection
Kaveh Eskandari Miandoab, Katharine Kowalyshyn, Kabir Pamnani +3
We present IntelliProof, an interactive system for analyzing argumentative essays through LLMs. IntelliProof structures an essay as an argumentation graph, where claims are represe…