3 papers
cs.AI2026
Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue
Kratika Bhagtani, Mrinal Anand, Yu Chen Xu +1
Existing voice AI assistants treat every detected pause as an invitation to speak. This works in dyadic dialogue, but in multi-party settings, where an AI assistant participates al…
cs.CL2026
Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
Yifei Li, Weidong Guo, Lingling Zhang +6
Long-term conversational memory is a core capability for LLM-based dialogue systems, yet existing benchmarks and evaluation protocols primarily focus on surface-level factual recal…
cs.IR2024
Improving Pinterest Search Relevance Using Large Language Models
Han Wang, Mukuntha Narayanan Sundararaman, Onur Gungor +5
To improve relevance scoring on Pinterest Search, we integrate Large Language Models (LLMs) into our search relevance model, leveraging carefully designed text representations to p…