Lune

EMNLP Findings2023

Mind the Gap Between Conversations for Improved Long-Term Dialogue Generation

Qiang Zhang, Jason Naradowsky, Yusuke Miyao

Abstract

Knowing how to end and resume conversations over time is a natural part of communication, allowing for discussions to span weeks, months, or years. The duration of gaps between conversations dictates which topics are relevant and which questions to ask, and dialogue systems which do not explicitly model time may generate responses that are unnatural. In this work we explore the idea of making dialogue models aware of time, and present GapChat, a multi-session dialogue dataset in which the time between each session varies. While the dataset is constructed in real-time, progress on events in speakers' lives is simulated in order to create realistic dialogues occurring across a long timespan. We expose time information to the model and compare different representations of time and event progress. In human evaluation we show that time-aware models perform better in metrics that judge the relevance of the chosen topics and the information gained from the conversation.

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.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Beyond Goldfish Memory: Long-Term Open-Domain Conversation cites Dense Passage Retrieval for Open-Domain Question Answering
  • Beyond Goldfish Memory: Long-Term Open-Domain Conversation cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  • 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
  • Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions cites Evaluating Very Long-Term Conversational Memory of LLM Agents
  • SHARE: Shared Memory-Aware Open-Domain Long-Term Dialogue Dataset Constructed from Movie Script cites Evaluating Very Long-Term Conversational Memory of LLM Agents
  • Evaluating Very Long-Term Conversational Memory of LLM Agents cites Beyond Goldfish Memory: Long-Term Open-Domain Conversation
  • Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework cites Evaluating Very Long-Term Conversational Memory of LLM Agents
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Evaluating Very Long-Term Conversational Memory of LLM AgentsAdyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal et al.ACL 2024 · 30 citations
  2. Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic InteractionsJihyoung Jang, Minwook Bae, Minji Kim, Dilek Hakkani-Tür et al.ACL 2025
  3. SHARE: Shared Memory-Aware Open-Domain Long-Term Dialogue Dataset Constructed from Movie ScriptEunwon Kim, Chanho Park, Buru ChangACL 2025
  4. Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose FrameworkCai Ke, Yiming Du, Bin Liang, Yifan Xiang et al.EMNLP 2025

Builds on11

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
  2. Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order SensitivityYao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel et al.ACL 2022 · 1,494 citations
  3. Beyond Goldfish Memory: Long-Term Open-Domain ConversationJing Xu, Arthur Szlam, Jason WestonACL 2022 · 329 citations
  4. Heuristic Evaluation of Conversational AgentsRaina Langevin, Ross J. Lordon, Thi Avrahami, Benjamin R. Cowan et al.CHI 2021 · 159 citations
  5. Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations

Related papers

  1. Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session ConversationsJihyoung Jang, Minseong Boo, Hyounghun KimEMNLP 2023 · 7 citations
  2. History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue SystemTong Zhang, Yong Liu, Boyang Li, Zhiwei Zeng et al.EMNLP Findings 2022 · 14 citations
  3. TIMEDIAL: Temporal Commonsense Reasoning in DialogLianhui Qin, Aditya Gupta, Shyam Upadhyay, Luheng He et al.ACL 2021
  4. Dialogue-Based Relation ExtractionDian Yu, Kai Sun, Claire Cardie, Dong YuACL 2020 · 106 citations
  5. Keep Me Updated! Memory Management in Long-term ConversationsSanghwan Bae, Dong-Hyun Kwak, Soyoung Kang, Min Young Lee et al.EMNLP Findings 2022 · 30 citations
Dusk over the sea between two cliffs drawn in fine vertical lines