AI & ML
CounselPlex: A Stressor-Aware Full-Duplex Counseling Model
arXiv cs.SD0 views
arXiv:2610.32702v1 Announce Type: cross Abstract: Full-duplex speech models can listen and speak at the same time, enabling natural, low-latency interaction. In counseling, however, these models often focus on the latest utterance and lose track of the seeker's underlying problem. We call this failure Stressor Blindness. We propose CounselPlex, a stressor-aware full-duplex framework that uses two operations. CounselPlex updates a short stressor state during seeker silence and injects this state into positions while listening. We also introduce RoPE Position Shift Augmentation (RPSA), which broadens positional coverage during training and improves performance at longer turn depths in our evaluation. LLM-judge evaluations show improved counseling quality and stressor grounding over strong baselines.
Source:https://arxiv.org/abs/2610.32702PreviousWhy Full-Duplex Speech Models Collapse in Long ConversationsNextVorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming
Related posts
SaaS Partner Scout: A Script for Identifying GitHub SaaS Project Contributors
0dev.to GitHub
WARN Act and Retaliation — Can Your Employer Punish You for Asking About a Layoff Notice?
0dev.to Data
WARN Act and Mental Health: What a Layoff Notice Does to Your Wellbeing, and Where to Get Support
0dev.to Data
Dimensionare un pallettizzatore dal lato del progettista: i tre numeri che non stanno nelle brochure
0dev.to Design
How to Choose the Best Stretch Tent Supplier for Your Next Purchase
0dev.to Design
How to spend three slow days in a city you have never visited
0dev.to Productivity