11 papers
GRASP: GRanularity-Aware Search Policy for Agentic RAG
Varun Gandhi, Jaewook Lee, Shantanu Todmal +4
Agentic retrieval-augmented generation (RAG) extends static RAG by allowing language models to iteratively reason, generate search queries, retrieve evidence, and predict answers.…
Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization
Jaewook Lee, Alexander Scarlatos, Simon Woodhead +1
With the emergence of large language models (LLMs) as a powerful class of generative artificial intelligence (AI), their use in tutoring has become increasingly prominent. Prior wo…
Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
Zhangqi Duan, Shuyan Huang, Alexander Scarlatos +3
A key part of developing large language model (LLM)-powered, automated tutoring tools is student simulation, i.e., using LLMs to role-play as students, which can facilitate tutor m…
Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures
Junyoung Park, Sunghwan Park, Seongyong Ju +1
Attack Success Rate (ASR) evaluates each jailbreak with a single yes/no label at the end of generation, telling us whether a failure happened but not how it unfolded. Two attacks t…
Simulated Students in Tutoring Dialogues: Substance or Illusion?
Alexander Scarlatos, Jaewook Lee, Simon Woodhead +1
Advances in large language models (LLMs) enable many new innovations in education. However, evaluating the effectiveness of new technology requires real students, which is time-con…
Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
Shuyan Huang, Alexander Scarlatos, Jaewook Lee +1
Recent advances in large language models (LLMs) have led to the development of AI-powered tutoring systems that provide interactive support via dialogue. To enable these tutoring s…