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

Name: Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
Uploaded: 2026-10-11T08:50:21.621636+00:00
Duration: 255 s
Description: The authors developed a retrieval-augmented generation (RAG) pipeline to automatically annotate pedagogical dialogue acts. They adapted the retrieval component by fine-tuning embeddings on tutoring data, achieving high accuracy without retraining the main language model. The method uses utterance-level indexing and context retrieval to improve annotation quality across different LLMs.

The authors developed a retrieval-augmented generation (RAG) pipeline to automatically annotate pedagogical dialogue acts. They adapted the retrieval component by fine-tuning embeddings on tutoring data, achieving high accuracy without retraining the main language model. The method uses utterance-level indexing and context retrieval to improve annotation quality across different LLMs.

Open the full episode