Context-Driven Incremental Compression for Multi-Turn Dialogue Generation (opens in new tab)  🔬ML Research  Content type: Academic

Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length. Naive truncation or summarization degrades fidelity, while existing context compressors lack cross-turn memory sharing or revision, causing information loss and compounding errors in long dialogues. We revisit the context compression under conversational dynamics and empiric...