SOURCE-LINKED INTELLIGENCE

Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely adopted for long-term conversational memory question answering. However, existing methods suffer from two key challenges: (1) fragmented evidence scattered across temporally distant sessions, and (2) noisy content within retrieved sessions that triggers the lost-in-the-middle effect. To address these challenges, we propose MemLoc, a unified Retrieve-Localize-Generate framework for long-term conversational memory QA. For retrieval, MemLoc decomposes e

Read original source ↗ Open in workspace

recordType

paper

region

Global