mlsanityData to 14 Oct 2026

Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems

arXiv 2506.00585 ↗First posted 31 May 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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 energy-based 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 48 references that are in the map. First posted on arXiv 31 May 2025.

Builds on

34 of 48 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  6. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  7. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  8. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  9. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 198
  10. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 138
  11. 2022RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encodercited by 118
  12. 2020Knowledge-Grounded Dialogue Generation with Pre-trained Language Modelscited by 107
22 more
  1. 2020Residual Energy-Based Models for Text Generationcited by 95
  2. 2020Sequential Latent Knowledge Selection for Knowledge-Grounded Dialoguecited by 82
  3. 2020Pre-Training Transformers as Energy-Based Cloze Modelscited by 52
  4. 2021Hindsight: Posterior-guided training of retrievers for improved open-ended generationcited by 38
  5. 2020Zero-Resource Knowledge-Grounded Dialogue Generationcited by 35
  6. 2021Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representationcited by 32
  7. 2024Leveraging LLMs for Unsupervised Dense Retriever Rankingcited by 19
  8. 2019Global Autoregressive Models for Data-Efficient Sequence Learningcited by 15
  9. 2022Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systemscited by 15
  10. 2021Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Modelscited by 14
  11. 2023RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modelingcited by 12
  12. 2020Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Modelscited by 10
  13. 2017Learning neural trans-dimensional random field language models with noise-contrastive estimationcited by 7
  14. 2023Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervisioncited by 7
  15. 2022A Challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systemscited by 6
  16. 2018Improved training of neural trans-dimensional random field language models with dynamic noise-contrastive estimationcited by 5
  17. 2017Language modeling with Neural trans-dimensional random fieldscited by 4
  18. 2022Information Extraction and Human-Robot Dialogue towards Real-life Tasks: A Baseline Study with the MobileCS Datasetcited by 4
  19. 2020Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Modelscited by 2
  20. 2022Discovering Customer-Service Dialog System with Semi-Supervised Learning and Coarse-to-Fine Intent Detectioncited by 2
  21. 2024The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)cited by 2
  22. 2023Exploring Energy-based Language Models with Different Architectures and Training Methods for Speech Recognitioncited by 1

Built on by

Not cited yet.