mlsanityData to 13 Oct 2026

Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting

arXiv 2409.12524 ↗First posted 19 Sep 2024cs.CL cs.AIcited by 2

On the map: Retrieval-augmented generation → Conversational and speech RAG

Abstract (arXiv)

While Retrieval-Augmented Generation (RAG) has shown promise in enhancing long-term conversations, the increasing memory load as conversations progress degrades retrieval accuracy. Drawing on psychological insights, we propose LUFY, a simple yet effective method that focuses on emotionally arousing memories and retains less than 10% of the conversation. In the user experiment, participants interacted with three types of RAG chatbots, each for 2 hours over 4 sessions, marking the most extensive assessment of a chatbot's long-term capabilities to date -- more than four times longer than any existing benchmark. The results demonstrate that prioritizing arousing memories while forgetting the majority of the conversation significantly enhances user experience. This study pushes the frontier of long-term conversations and highlights the importance of forgetting unimportant parts of conversations. Code and Dataset: https://github.com/ryuichi-sumida/LUFY, Hugginface Dataset:https://huggingface.co/datasets/RuiSumida/LUFY

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation. Builds on 18 of its 48 references that are in the map. First posted on arXiv 19 Sep 2024.

Builds on

18 of 48 references.

References · 18

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,322
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,492
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,281
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,541
  5. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,535
  6. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  7. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 551
  8. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  9. 2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 166
  10. 2022TimeLMs: Diachronic Language Models from Twittercited by 129
  11. 2023DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4cited by 129
  12. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 119
6 more
  1. 2022EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysiscited by 75
  2. 2022Keep Me Updated! Memory Management in Long-term Conversationscited by 63
  3. 2024In Defense of RAG in the Era of Long-Context Language Modelscited by 53
  4. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Managementcited by 50
  5. 2023Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversationscited by 47
  6. 2023Effortless Integration of Memory Management into Open-Domain Conversation Systemscited by 3

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactionscited by 3
  2. 2026MemUse: Moving Memory Evaluation from Direct QA to Natural Integration in Long-Term Human-AI Conversationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents
  2. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
  3. 2026ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support
  4. 2025REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation
  5. 2025MMAG: Mixed Memory-Augmented Generation for Large Language Models Applications
  6. 2024Ever-Evolving Memory by Blending and Refining the Past
  7. 2024Adaptive Retrieval-Augmented Generation for Conversational Systems
  8. 2025Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG