How Evidence Generation Boosts Document-Grounded Dialogue with LLMs

This study introduces DGDE, a document‑grounded dialogue framework that leverages large language model‑generated evidence, combining retrieval, reranking, fine‑tuning, and iterative question correction to markedly improve accuracy, comprehensiveness, coherence, and completeness on the Doc2dial benchmark.

Evidence generationFine-tuningdocument-grounded dialogue

0 likes · 21 min read

How Evidence Generation Boosts Document-Grounded Dialogue with LLMs