CounselReflect: A Toolkit for Auditing Mental-Health Dialogues

View PDF HTML (experimental)

Abstract:Mental-health support is increasingly mediated by conversational systems (e.g., LLM-based tools), but users often lack structured ways to audit the quality and potential risks of the support they receive. We introduce CounselReflect, an end-to-end toolkit for auditing mental-health support dialogues. Rather than producing a single opaque quality score, CounselReflect provides structured, multi-dimensional reports with session-level summaries, turn-level scores, and evidence-linked excerpts to support transparent inspection. The system integrates two families of evaluation signals: (i) 12 model-based metrics produced by task-specific predictors, and (ii) rubric-based metrics that extend coverage via a literature-derived library (69 metrics) and user-defined custom metrics, operationalized with configurable LLM judges. CounselReflect is available as a web application, browser extension, and command-line interface (CLI), enabling use in real-time settings as well as at scale. Human evaluation includes a user study with 20 participants and an expert review with 6 mental-health professionals, suggesting that CounselReflect supports understandable, usable, and trustworthy auditing. A demo video and full source code are also provided.

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2603.29429 [cs.CL]

(or arXiv:2603.29429v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2603.29429

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yahan Li [view email] [v1] Tue, 31 Mar 2026 08:35:43 UTC (1,828 KB)