SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
[Przetwarzanie języka] Autorzy: Haobo Zheng, Tan Tang, Yan Chen i 2 więcej
Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what information is shared by the group, and how states change over time. Recent studies on multi-party dialogue benchmarks show that existing general-purpose LLM memory systems tend to lose person and group relations or struggle to integrate clues distributed across members, groups, and time. Together, these issues reveal two core bottlenecks: message attribution and relational understanding in multi-party dialogue, and state reconstruction from interleaved histories. To address both, we propose $\textbf{SpeakerMem-R1}$: its dual-track memory stores speaker-labeled verbatim messages and derived states organized into person-level and group-level views, th…
- Kategoria arxiv
- cs.CL
- Kategoria
- Przetwarzanie języka