mlsanityData to 7 Oct 2026

Long Time No See! Open-Domain Conversation with Long-Term Persona Memory

arXiv 2203.05797 ↗First posted 11 Mar 2022cs.CLcited by 107

Not on the map. Why?

Cited by 21 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Most of the open-domain dialogue models tend to perform poorly in the setting of long-term human-bot conversations. The possible reason is that they lack the capability of understanding and memorizing long-term dialogue history information. To address this issue, we present a novel task of Long-term Memory Conversation (LeMon) and then build a new dialogue dataset DuLeMon and a dialogue generation framework with Long-Term Memory (LTM) mechanism (called PLATO-LTM). This LTM mechanism enables our system to accurately extract and continuously update long-term persona memory without requiring multiple-session dialogue datasets for model training. To our knowledge, this is the first attempt to conduct real-time dynamic management of persona information of both parties, including the user and the bot. Results on DuLeMon indicate that PLATO-LTM can significantly outperform baselines in terms of long-term dialogue consistency, leading to better dialogue engagingness.

Key facts. Cited by 107 papers in the map (data through 7 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 11 Mar 2022.

Builds on

20 of 29 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  4. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  5. 2020Recipes for building an open-domain chatbotcited by 593
  6. 2020Towards a Human-like Open-Domain Chatbotcited by 467
  7. 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
  8. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  9. 2019ERNIE 2.0: A Continual Pre-training Framework for Language Understandingcited by 230
  10. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  11. 2016A Persona-Based Neural Conversation Modelcited by 221
  12. 2019The Second Conversational Intelligence Challenge (ConvAI2)cited by 178
8 more
  1. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
  2. 2018Training Millions of Personalized Dialogue Agentscited by 126
  3. 2020PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learningcited by 79
  4. 2019Personalized Dialogue Generation with Diversified Traitscited by 73
  5. 2020Towards Persona-Based Empathetic Conversational Modelscited by 53
  6. 2021PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generationcited by 37
  7. 2020XPersona: Evaluating Multilingual Personalized Chatbotcited by 36
  8. 2017Neural Personalized Response Generation as Domain Adaptationcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 31; 2024: 34; 2025: 21; 2026: 18.

107 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  3. 2023A Comprehensive Overview of Large Language Modelscited by 639
  4. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  5. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 204
  6. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 203
  7. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  8. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 163
  9. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialoguecited by 121
  10. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 94
  11. 2025MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agentscited by 82
  12. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
38 more
  1. 2023Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memorycited by 64
  2. 2022Keep Me Updated! Memory Management in Long-term Conversationscited by 62
  3. 2023Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Modelscited by 62
  4. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Managementcited by 50
  5. 2026Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agentscited by 49
  6. 2023You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instrumentscited by 48
  7. 2023Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversationscited by 47
  8. 2024The Oscars of AI Theater: A Survey on Role-Playing with Language Modelscited by 47
  9. 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applicationscited by 40
  10. 2022PAL: Persona-Augmented Emotional Support Conversation Generationcited by 39
  11. 2024UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systemscited by 38
  12. 2024Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphscited by 38
  13. 2023Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agentscited by 36
  14. 2024Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversationscited by 36
  15. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topicscited by 36
  16. 2024PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answeringcited by 34
  17. 2024The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Surveycited by 32
  18. 2026From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agentscited by 29
  19. 2023LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streamingcited by 27
  20. 2024Circuit Complexity Bounds for RoPE-based Transformer Architecturecited by 26
  21. 2025A Survey of Personalization: From RAG to Agentcited by 26
  22. 2023MPCHAT: Towards Multimodal Persona-Grounded Conversationcited by 24
  23. 2025Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalizationcited by 24
  24. 2024Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Timecited by 22
  25. 2023RoleEval: A Bilingual Role Evaluation Benchmark for Large Language Modelscited by 21
  26. 2025StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turnscited by 20
  27. 2023PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narrativescited by 19
  28. 2024Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluationscited by 19
  29. 2024Understanding the Impact of Long-Term Memory on Self-Disclosure with Large Language Model-Driven Chatbots for Public Health Interventioncited by 15
  30. 2023ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Humancited by 14
  31. 2023Leveraging Large Language Models for Automated Dialogue Analysiscited by 14
  32. 2023Mind the Gap Between Conversations for Improved Long-Term Dialogue Generationcited by 13
  33. 2024MPCODER: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learningcited by 12
  34. 2025Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challengescited by 12
  35. 2025Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactionscited by 12
  36. 2023TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaborationcited by 11
  37. 2023MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Controlcited by 11
  38. 2024The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trendscited by 11

50 most cited of 107 All 107 (JSON)