mlsanityData to 7 Oct 2026

Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations

arXiv 2402.11975 ↗First posted 19 Feb 2024cs.CLcited by 36

Not on the map. Why?

Abstract (arXiv)

Existing retrieval-based methods have made significant strides in maintaining long-term conversations. However, these approaches face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. This study introduces a novel framework, COmpressive Memory-Enhanced Dialogue sYstems (COMEDY), which eschews traditional retrieval modules and memory databases. Instead, COMEDY adopts a "One-for-All" approach, utilizing a single language model to manage memory generation, compression, and response generation. Central to this framework is the concept of compressive memory, which intergrates session-specific summaries, user-bot dynamics, and past events into a concise memory format. To support COMEDY, we curated a large-scale Chinese instruction-tuning dataset, Dolphin, derived from real user-chatbot interactions. Comparative evaluations demonstrate COMEDY's superiority over traditional retrieval-based methods in producing more nuanced and human-like conversational experiences. Our codes are available at https://github.com/nuochenpku/COMEDY.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 28 of its 45 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

28 of 45 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  8. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  9. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  10. 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
  11. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
  12. 2023Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERTcited by 155
16 more
  1. 2023Towards Making the Most of ChatGPT for Machine Translationcited by 138
  2. 2022Long Time No See! Open-Domain Conversation with Long-Term Persona Memorycited by 107
  3. 2023Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Modelscited by 87
  4. 2023ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmarkcited by 77
  5. 2020Memformer: A Memory-Augmented Transformer for Sequence Modelingcited by 63
  6. 2022Keep Me Updated! Memory Management in Long-term Conversationscited by 62
  7. 2023Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observationscited by 58
  8. 2021Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answeringcited by 39
  9. 2022End-to-end Spoken Conversational Question Answering: Task, Dataset and Modelcited by 37
  10. 2020Adaptive Bi-directional Attention: Exploring Multi-Granularity Representations for Machine Reading Comprehensioncited by 22
  11. 2023History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue Systemcited by 15
  12. 2023From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Promptingcited by 10
  13. 2021Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentationcited by 9
  14. 2022Xu at SemEval-2022 Task 4: Pre-BERT Neural Network Methods vs Post-BERT RoBERTa Approach for Patronizing and Condescending Language Detectioncited by 3
  15. 2023Effortless Integration of Memory Management into Open-Domain Conversation Systemscited by 3
  16. 2023Improve Retrieval-based Dialogue System via Syntax-Informed Attentioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 10; 2026: 22.

36 papers.

Sort:

By area:

  1. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 101
  2. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Managementcited by 50
  3. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 49
  4. 2024The Oscars of AI Theater: A Survey on Role-Playing with Language Modelscited by 47
  5. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topicscited by 36
  6. 2025Cognitive Memory in Large Language Modelscited by 28
  7. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agentscited by 27
  8. 2025Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMscited by 22
  9. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memorycited by 19
  10. 2025Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialoguecited by 17
  11. 2025MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialoguescited by 8
  12. 2026All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolutioncited by 8
24 more
  1. 2024SHARE: Shared Memory-Aware Open-Domain Long-Term Dialogue Dataset Constructed from Movie Scriptcited by 6
  2. 2026MemRefine: LLM-Guided Compression for Long-Term Agent Memorycited by 6
  3. 2025Codifying Character Logic in Role-Playingcited by 5
  4. 2025Role-Playing Evaluation for Large Language Modelscited by 5
  5. 2026MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agentscited by 3
  6. 2026MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversationcited by 2
  7. 2026Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memorycited by 2
  8. 2026From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agentscited by 2
  9. 2026PGMem: Tightly Coupled Persona-Memory Graph for Lifelong Personalized Agentscited by 2
  10. 2026When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational Agentscited by 2
  11. 2026G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agentscited by 1
  12. 2026Ontology Memory-Augmented ASR Correction for Long Text-Speech Interleaved Conversationscited by 1
  13. 2026Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challengescited by 1
  14. 2026Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoningcited by 1
  15. 2026Scene-Aware Memory Discrimination: Deciding Which Personal Knowledge Stayscited by 0
  16. 2026SOMA: Efficient Multi-turn LLM Serving via Small Language Modelcited by 0
  17. 2026Improving Multi-turn Dialogue Consistency with Self-Recall Thinkingcited by 0
  18. 2026DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memorycited by 0
  19. 2026Enhancing Software Engineering Through Closed-Loop Memory Optimizationcited by 0
  20. 2026EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigationcited by 0
  21. 2026Memory Makes the Difference: Evaluating How Different Memory Roles Shape Conversational Agentscited by 0
  22. 2026ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agentscited by 0
  23. 2026Interactive Memory Learning for Long-Term Conversationscited by 0
  24. 2026AMU:Admission and Memory Update for Personalized Conversations---Structured Memory with SLM Guided Controlcited by 0