Efficient Latent Variable Modeling for Knowledge-Grounded Dialogue Generation
Abstract Knowledge-grounded dialogue generation requires first retrieving appropriate
external knowledge based on a conversational context and then generating a response …
external knowledge based on a conversational context and then generating a response …
KCTS: knowledge-constrained tree search decoding with token-level hallucination detection
Large Language Models (LLMs) have demonstrated remarkable human-level natural
language generation capabilities. However, their potential to generate misinformation, often …
language generation capabilities. However, their potential to generate misinformation, often …
Enhancing Knowledge Selection via Multi-level Document Semantic Graph
RH Zhang, T Yongmei - … of the 2024 Joint International Conference …, 2024 - aclanthology.org
Abstract Knowledge selection is a crucial sub-task of Document Grounded Dialogue System.
Existing methods view knowledge selection as a sentence matching or classification …
Existing methods view knowledge selection as a sentence matching or classification …
対話破綻検出と知識の興味深さに基づく雑談応答生成手法の提案
小野関宏己, 稲葉通将 - 人工知能学会研究会資料 言語・音声理解と …, 2024 - jstage.jst.go.jp
抄録 Open-domain dialogue systems have been increasingly applied in various situations,
with a growing need to improve user engagement. One effective approach is to generate …
with a growing need to improve user engagement. One effective approach is to generate …