LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, and Dong Yu, in ICLR, 2025.

Code

Download the full text

Abstract

Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in sustained interactions remain underexplored. We introduce LongMemEval, a comprehensive benchmark designed to evaluate five core long-term memory abilities of chat assistants: information extraction, multi-session reasoning, temporal reasoning, knowledge updates, and abstention. With 500 meticulously curated questions embedded within freely scalable user-assistant chat histories, LongMemEval presents a significant challenge to existing long-term memory systems, with commercial chat assistants and long-context LLMs showing a 30% accuracy drop on memorizing information across sustained interactions. We then present a unified framework that breaks down the long-term memory design into three stages: indexing, retrieval, and reading. Built upon key experimental insights, we propose several memory design optimizations including session decomposition for value granularity, fact-augmented key expansion for indexing, and time-aware query expansion for refining the search scope. Extensive experiments show that these optimizations greatly improve both memory recall and downstream question answering on LongMemEval. Overall, our study provides valuable resources and guidance for advancing the long-term memory capabilities of LLM-based chat assistants, paving the way toward more personalized and reliable conversational AI.

Source Code

Bib Entry

@inproceedings{wu2025longmemeval,
  title = {LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory},
  author = {Wu, Di and Wang, Hongwei and Yu, Wenhao and Zhang, Yuwei and Chang, Kai-Wei and Yu, Dong},
  booktitle = {ICLR},
  year = {2025}
}

Related Publications

DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning, EMNLP, 2025
SNaRe: Domain-aware Data Generation for Low-Resource Event Detection, EMNLP, 2025
SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness, EMNLP, 2024
TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction, ACL-Findings, 2024
Event Detection from Social Media for Epidemic Prediction, NAACL, 2024
GENEVA: Pushing the Limit of Generalizability for Event Argument Extraction with 100+ Event Types, ACL, 2023
TAGPRIME: A Unified Framework for Relational Structure Extraction, ACL, 2023
Enhancing Unsupervised Semantic Parsing with Distributed Contextual Representations, ACL-Finding, 2023
DEGREE: A Data-Efficient Generative Event Extraction Model, NAACL, 2022
Intent Classification and Slot Filling for Privacy Policies, ACL, 2021