THEANINE: Revisiting Memory Management in Long-term Conversations with Timeline-augmented Response Generation

Seo Hyun Kim, kai tzu-iunn ong, Taeyoon Kwon, Namyoung Kim, Keummin Ka, SeongHyeon Bae, Yohan Jo, SeungWon Hwang, Dongha Lee, Jinyoung Yeom

THEANINE: Revisiting Memory Management in Long-term Conversations with Timeline-augmented Response Generation: 35 upvotes on Hugging Face Daily Papers, #4 of 29 papers on 2024-06-18. Day-by-day upvote history.

Large language models (LLMs) are capable of processing lengthy dialogue histories during prolonged interaction with users without additional memory modules; however, their responses tend to overlook or incorrectly recall information from the past. In this paper, we revisit memory-augmented response generation in the era of LLMs. While prior work focuses on getting rid of outdated memories, we argue that such memories can provide contextual cues that help dialogue systems understand the development of past events and, therefore, benefit response generation. We present Theanine, a framework that augments LLMs' response generation with memory timelines -- series of memories that demonstrate the development and causality of relevant past events. Along with Theanine, we introduce TeaFarm, a counterfactual-driven question-answering pipeline addressing the limitation of G-Eval in long-term conversations. Supplementary videos of our methods and the TeaBag dataset for TeaFarm evaluation are in https://theanine-693b0.web.app/.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.