8 papers
Impact of Multimodal and Conversational AI on Learning Outcomes and Experience
Karan Taneja, Anjali Singh, Ashok K. Goel
Multimodal Large Language Models (MLLMs) offer an opportunity to support multimedia learning through conversational systems grounded in educational content. However, while conversa…
HALT: Hallucination Assessment via Log-probs as Time series
Ahmad Shapiro, Karan Taneja, Ashok Goel
Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination Assessment via Log-probs as Time seri…
Towards a Multimodal Document-grounded Conversational AI System for Education
Karan Taneja, Anjali Singh, Ashok K. Goel
Multimedia learning using text and images has been shown to improve learning outcomes compared to text-only instruction. But conversational AI systems in education predominantly re…
MuDoC: An Interactive Multimodal Document-grounded Conversational AI System
Karan Taneja, Ashok K. Goel
Multimodal AI is an important step towards building effective tools to leverage multiple modalities in human-AI communication. Building a multimodal document-grounded AI system to…
Self-Explanation in Social AI Agents
Rhea Basappa, Mustafa Tekman, Hong Lu +3
Social AI agents interact with members of a community, thereby changing the behavior of the community. For example, in online learning, an AI social assistant may connect learners…
Can Active Label Correction Improve LLM-based Modular AI Systems?
Karan Taneja, Ashok Goel
Modular AI systems can be developed using LLM-prompts-based modules to minimize deployment time even for complex tasks. However, these systems do not always perform well and improv…