Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Move by Move: Measuring and Steering How LLMs Conduct Psychotherapy

Afonso Baldo, Hugo Pitorro, Areti Vassilopoulos, Anabela C. Areias +4 more

Published

Aug 21, 2026

Citations

0

Trust level

Moderate

Usefulness score

65/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Aug 21, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Expert Verification General

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction. We introduce an ontology of ten therapeutic moves: compact, function-based categories grounded in the MULTI-60 inventory, validated through an annotation campaign with five licensed psychologists, and scaled with a judge-based approach that matches expert agreement. Applying it to real counseling transcripts and model-led sessions, we compare the move distributions between human clinicians and a panel of frontier models. Models over-use inquiry at up to three times the human rate, neglect psychoeducation, and are strongly context-anchored: they carry forward strategies initiated by a human clinician but rarely initiate them themselves. Exposing the ontology as a set of tools roughly halves the mean deviation from the human move distribution and improves turn-level alignment with human therapist by 7-9 percentage points, without any fine-tuning.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Expert Verification

Directly usable for protocol triage.

"Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction."

Reported Metrics

strong

Agreement

Useful for evaluation criteria comparison.

"We introduce an ontology of ten therapeutic moves: compact, function-based categories grounded in the MULTI-60 inventory, validated through an annotation campaign with five licensed psychologists, and scaled with a judge-based approach that matches expert agreement."

Rater Population

strong

Domain Experts

Helpful for staffing comparability.

"We introduce an ontology of ten therapeutic moves: compact, function-based categories grounded in the MULTI-60 inventory, validated through an annotation campaign with five licensed psychologists, and scaled with a judge-based approach that matches expert agreement."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

agreement
Human feedback details
Uses human feedback
Yes
Feedback types
Expert Verification
Rater population
Domain Experts
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction.
  • We introduce an ontology of ten therapeutic moves: compact, function-based categories grounded in the MULTI-60 inventory, validated through an annotation campaign with five licensed psychologists, and scaled with a judge-based approach that matches expert agreement.
  • Applying it to real counseling transcripts and model-led sessions, we compare the move distributions between human clinicians and a panel of frontier models.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Expert verification evaluation Agreement / Kappa

Contribution summary

  • We introduce an ontology of ten therapeutic moves: compact, function-based categories grounded in the MULTI-60 inventory, validated through an annotation campaign with five licensed psychologists, and scaled with a judge-based approach that…
  • Applying it to real counseling transcripts and model-led sessions, we compare the move distributions between human clinicians and a panel of frontier models.
  • Models over-use inquiry at up to three times the human rate, neglect psychoeducation, and are strongly context-anchored: they carry forward strategies initiated by a human clinician but rarely initiate them themselves.

Why it matters for eval

  • We introduce an ontology of ten therapeutic moves: compact, function-based categories grounded in the MULTI-60 inventory, validated through an annotation campaign with five licensed psychologists, and scaled with a judge-based approach that…
  • Applying it to real counseling transcripts and model-led sessions, we compare the move distributions between human clinicians and a panel of frontier models.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Expert Verification

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: agreement