The Flow has not summarised this story yet — read it at arXiv Machine Learning.
The paper introduces a method to predict whether volunteer mental‑health crisis counselors will improve their conversational skills early in their careers. It focuses on identifying moments counselors initially struggle with, tracking how they adapt to similar moments in later conversations, and using these early adaptations to forecast long‑term improvement. The approach outperforms baseline models that rely solely on conversation transcripts.
The paper introduces FIGS, a dual‑axis evaluation framework for multi‑turn sycophancy that avoids penalizing empathy. It uses a 10‑turn conversational simulator with 500 diverse scenarios to test whether models stay truthful while keeping praise proportional, and whether they show calibrated validation of user feelings. The study finds that current models either drift toward sycophancy or become overly detached, highlighting an unresolved trade‑off in sustained dialogue.
arXiv:2601. 00181v3 Announce Type: replace-cross Abstract: We address two persistent gaps in Emotion Recognition in Conversation: which modeling choices materially affect performance, and how recognition findings connect to interpretable discourse-level patterns.
arXiv:2609.17180v1 Announce Type: new Abstract: Multimodal counselor response generation (MCRG) aims to generate an appropriate counselor response from multimodal dialogue histories. Progress is limi...
arXiv:2609.14118v1 Announce Type: cross Abstract: Online understanding of who is talking to the camera wearer is a key capability for egocentric social interaction. However, existing talk-to-me (TTM)...
arXiv:2607. 24191v1 Announce Type: cross Abstract: Conversational stance detection has shifted from static text analysis to dynamic multimodal modeling.