4 papers
TeachLM: Post-Training LLMs for Education Using Authentic Learning Data
Janos Perczel, Jin Chow, Dorottya Demszky
The promise of generative AI to revolutionize education is constrained by the pedagogical limits of large language models (LLMs). A major issue is the lack of access to high-qualit…
Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes
Li Lucy, Camilla Griffiths, Sarah Levine +3
Conventional bag-of-words approaches for topic modeling, like latent Dirichlet allocation (LDA), struggle with literary text. Literature challenges lexical methods because narrativ…
Multi-Stage Speaker Diarization for Noisy Classrooms
Ali Sartaz Khan, Tolulope Ogunremi, Ahmed Adel Attia +1
Speaker diarization, the process of identifying "who spoke when" in audio recordings, is essential for understanding classroom dynamics. However, classroom settings present distinc…
Problem-Oriented Segmentation and Retrieval: Case Study on Tutoring Conversations
Rose E. Wang, Pawan Wirawarn, Kenny Lam +2
Many open-ended conversations (e.g., tutoring lessons or business meetings) revolve around pre-defined reference materials, like worksheets or meeting bullets. To provide a framewo…