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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lee, Jinsook, Vanacore, Kirk, Zhou, Zhuqian, Ahtisham, Bakhtawar, Kizilcec, Rene F.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908934984433664
author Lee, Jinsook
Vanacore, Kirk
Zhou, Zhuqian
Ahtisham, Bakhtawar
Kizilcec, Rene F.
author_facet Lee, Jinsook
Vanacore, Kirk
Zhou, Zhuqian
Ahtisham, Bakhtawar
Kizilcec, Rene F.
contents 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 demonstrations. Evaluated across two real tutoring dialogue datasets (TalkMoves and Eedi) and three LLM backbones (GPT-5.2, Claude Sonnet 4.6, Qwen3-32b), our best configuration achieves Cohen's $κ$ of 0.526-0.580 on TalkMoves and 0.659-0.743 on Eedi, substantially outperforming no-retrieval baselines ($κ= 0.275$-$0.413$ and $0.160$-$0.410$). An ablation study reveals that utterance-level indexing, rather than embedding quality alone, is the primary driver of these gains, with top-1 label match rates improving from 39.7\% to 62.0\% on TalkMoves and 52.9\% to 73.1\% on Eedi under domain-adapted retrieval. Retrieval also corrects systematic label biases present in zero-shot prompting and yields the largest improvements for rare and context-dependent labels. These findings suggest that adapting the retrieval component alone is a practical and effective path toward expert-level pedagogical dialogue annotation while keeping the generative model frozen.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03127
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
Lee, Jinsook
Vanacore, Kirk
Zhou, Zhuqian
Ahtisham, Bakhtawar
Kizilcec, Rene F.
Computation and Language
Artificial Intelligence
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 demonstrations. Evaluated across two real tutoring dialogue datasets (TalkMoves and Eedi) and three LLM backbones (GPT-5.2, Claude Sonnet 4.6, Qwen3-32b), our best configuration achieves Cohen's $κ$ of 0.526-0.580 on TalkMoves and 0.659-0.743 on Eedi, substantially outperforming no-retrieval baselines ($κ= 0.275$-$0.413$ and $0.160$-$0.410$). An ablation study reveals that utterance-level indexing, rather than embedding quality alone, is the primary driver of these gains, with top-1 label match rates improving from 39.7\% to 62.0\% on TalkMoves and 52.9\% to 73.1\% on Eedi under domain-adapted retrieval. Retrieval also corrects systematic label biases present in zero-shot prompting and yields the largest improvements for rare and context-dependent labels. These findings suggest that adapting the retrieval component alone is a practical and effective path toward expert-level pedagogical dialogue annotation while keeping the generative model frozen.
title Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.03127