ACL Findings2025
Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems
Yucheng Cai, Ke Li, Yi Huang, Junlan Feng, Zhijian Ou
Abstract
A retriever, which retrieves relevant knowledge pieces from a knowledge base given a context, is an important component in many natural language processing (NLP) tasks. Retrievers have been introduced in knowledge-grounded dialog systems to improve knowledge acquisition. In knowledge-grounded dialog systems, when conditioning on a given context, there may be multiple relevant and correlated knowledge pieces. However, knowledge pieces are usually assumed to be conditionally independent in current retriever models. To address this issue, we propose Entriever, an energybased retriever. Entriever directly models the candidate retrieval results as a whole instead of modeling the knowledge pieces separately, with the relevance score defined by an energy function. We explore various architectures of energy functions and different training methods for Entriever, and show that Entriever substantially outperforms the strong cross-encoder baseline in knowledge retrieval tasks. Furthermore, we show that in semi-supervised training of knowledge-grounded dialog systems, Entriever enables effective scoring of retrieved knowledge pieces and significantly improves end-to-end performance of dialog systems.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Dense Passage Retrieval for Open-Domain Question Answering cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks cites Dense Passage Retrieval for Open-Domain Question Answering
- Knowledge-Grounded Dialogue Generation with Pre-trained Language Models cites Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
Builds on12
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- Sequential Latent Knowledge Selection for Knowledge-Grounded DialogueByeongchang Kim, Jaewoo Ahn, Gunhee KimICLR 2020 · 179 citations
- Knowledge-Grounded Dialogue Generation with Pre-trained Language ModelsXueliang Zhao, Wei Wu, Can Xu, Chongyang Tao et al.EMNLP 2020 · 153 citations
- Residual Energy-Based Models for Text GenerationYuntian Deng, Anton Bakhtin, Myle Ott, Arthur Szlam et al.ICLR 2020 · 147 citations
- Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations
Related papers
- Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented DialogFanqi Wan, Weizhou Shen, Ke Yang, Xiaojun Quan et al.ACL 2023 · 14 citations
- Efficient Latent Variable Modeling for Knowledge-Grounded Dialogue GenerationGunsoo Han, Daejin Jo, Daniel Wontae Nam, Eunseop Yoon et al.EMNLP Findings 2023
- Lexical Knowledge Internalization for Neural Dialog GenerationZhiyong Wu, Wei Bi, Xiang Li, Lingpeng Kong et al.ACL 2022
- Hindsight: Posterior-guided training of retrievers for improved open-ended generationAshwin Paranjape, Omar Khattab, Christopher Potts, Matei Zaharia et al.ICLR 2022 · 48 citations
- Learning to Match Representations is Better for End-to-End Task-Oriented Dialog SystemWanshi Xu, Xuxin Cheng, Zhihong Zhu, Zhanpeng Chen et al.EMNLP Findings 2024
