Year: 2026
Type: preprint
Abstract: Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts. While recent LLMs support extended context windows, efficient management of dialogue history in practice is needed due to inference cost and latency constraints. We present DyCP, a lightweight context management method implemented outside the LLM that dynamically identifies and retrieves relevant dialogue segments conditioned on the current turn, without offline memory construction. DyCP manages dialogue context while preserving the sequential nature of dialogue without predefined topic boundaries, enabling adaptive and efficient context selection. Across three long-form dialogue benchmarks-LoCoMo, MT-Bench+, and SCM4LLMs-and multiple LLM backends, DyCP achieves competitive answer quality in downstream generation, with more selective context usage and improved inference efficiency.
Source: arXiv (Cornell University)
Authors: Choi, Nayoung, Zhang, Jonathan, Choi, Jinho D.
Institution: Emory University
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7124162267
Cites:
Cited by:
Related to: