arXiv AI By Keita Kiuchi, Yoshikazu Fujimoto, Hideyuki Got\=o, Tomonori Hosokawa, Makoto Nishimura, Y\=osuke Sat\=o, Izumi Sezai, Tomohiro Inoue

Distinct Profiles of Run-to-Run Score Reliability and Expert-Panel Alignment Across Four LLM Evaluators of Simulated Japanese-Language AI-to-AI Counseling

Read the original on arXiv AI →

The study examined how four large language models (GPT‑5.5, Gemini 3.5 Flash, Claude Opus 4.8, and Fable 5) scored 18 simulated Japanese‑language AI‑to‑AI counseling sessions compared to ratings from 15 human counseling experts. Each model evaluated every transcript three times on four motivational‑interviewing‑informed dimensions and overall quality, consistently giving higher scores for softening sustain talk and overall quality than the expert panel, though the magnitude varied by model. Run‑to‑run reliability (intraclass correlation coefficients ranging from .33 to .96) did not predict closer alignment with expert judgments, and the models’ ability to discriminate counselor conditions was distinct from both reliability and alignment.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Jul 1

Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support

arXiv:2606. 30887v1 Announce Type: cross Abstract: Large language models show promise for mental health support, yet therapeutic quality improves only when evaluation functions as an actionable control signal rather than a passive metric.

By Mizanur Rahman, Abeer Badawi, Elahe Rahimi, Laleh Seyyed-Kalantari, Frank Rudzicz, Enamul Hoque, Elham Dolatabadi
arXiv Computation and Language
Aug 28

Beyond Reflection: Affirmation as a Promising Behavioral Marker Associated with Quality in Text-Based Counseling

The paper investigates which counselor behaviors correlate with higher dialogue quality in AI-assisted text-based counseling. Using the KokoroChat dataset, the authors find that the strategy of affirmation consistently associates with better session quality, more so than reflection. Cross-dataset experiments suggest this signal also appears, to some extent, in an English dataset of non-expert supporters.

By Michimasa Inaba