Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts

ArXi:2604.03127v1 Announce Type: cross Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient domain grounding. We present a domain-adapted RAG pipeline for tutoring move annotation. Rather than fine-tuning the generative model, we adapt retrieval by fine-tuning a lightweight embedding model on tutoring corpora and indexing dialogues at the utterance level to retrieve labeled few-shot nstrations.