@inproceedings{cui-etal-2026-measuring,
title = "Measuring the quality of therapy sessions against assessment scales using augmented semantic-similarity approaches",
author = "Cui, Kejian and
D{'}alfonso, Simon and
Conway, Mike",
editor = "Zirikly, Aya and
Bar, Kfir and
MacAvaney, Sean and
Ireland, Molly and
Ophir, Yaakov and
Atzil-Slonim, Dana and
Varadarajan, Vasudha and
Bedrick, Steven and
Desmet, Bart",
booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology ({CLP}sych 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.clpsych-1.22/",
pages = "271--281",
ISBN = "979-8-89176-421-7",
abstract = "Therapist fidelity and competence rating scales provide a way to measure quality assurance and therapist training outcomes. Scores on these scales reflect the extent to which a therapist adheres to specific therapeutic principles during a psychotherapy session. Existing research has employed natural language processing (NLP) techniques to automatically predict scale ratings. However, existing approaches require a model trained on a dataset of therapy sessions annotated with the target rating scale.Recent work has explored directly inferring therapeutic alliance by computing semantic similarity between therapy transcripts and the Working Alliance Inventory, via cosine similarity between sentence embeddings.In this paper, we extend this line of work by computing semantic similarity between therapist talk turns and therapist fidelity scale items to directly infer fidelity to specific therapeutic modalities. We further enhance this method by augmentation with LLM-generated example therapist utterances that instantiate target behaviours (as expressed by scale items) across varied therapeutic contexts.In evaluations on two independent datasets, our example-augmented semantic similarity approach consistently shows effectiveness in discriminating therapeutic modalities and levels of therapist fidelity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cui-etal-2026-measuring">
<titleInfo>
<title>Measuring the quality of therapy sessions against assessment scales using augmented semantic-similarity approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kejian</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">D’alfonso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Conway</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aya</namePart>
<namePart type="family">Zirikly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kfir</namePart>
<namePart type="family">Bar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">MacAvaney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Molly</namePart>
<namePart type="family">Ireland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaakov</namePart>
<namePart type="family">Ophir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Atzil-Slonim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasudha</namePart>
<namePart type="family">Varadarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bedrick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bart</namePart>
<namePart type="family">Desmet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-421-7</identifier>
</relatedItem>
<abstract>Therapist fidelity and competence rating scales provide a way to measure quality assurance and therapist training outcomes. Scores on these scales reflect the extent to which a therapist adheres to specific therapeutic principles during a psychotherapy session. Existing research has employed natural language processing (NLP) techniques to automatically predict scale ratings. However, existing approaches require a model trained on a dataset of therapy sessions annotated with the target rating scale.Recent work has explored directly inferring therapeutic alliance by computing semantic similarity between therapy transcripts and the Working Alliance Inventory, via cosine similarity between sentence embeddings.In this paper, we extend this line of work by computing semantic similarity between therapist talk turns and therapist fidelity scale items to directly infer fidelity to specific therapeutic modalities. We further enhance this method by augmentation with LLM-generated example therapist utterances that instantiate target behaviours (as expressed by scale items) across varied therapeutic contexts.In evaluations on two independent datasets, our example-augmented semantic similarity approach consistently shows effectiveness in discriminating therapeutic modalities and levels of therapist fidelity.</abstract>
<identifier type="citekey">cui-etal-2026-measuring</identifier>
<location>
<url>https://aclanthology.org/2026.clpsych-1.22/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>271</start>
<end>281</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring the quality of therapy sessions against assessment scales using augmented semantic-similarity approaches
%A Cui, Kejian
%A D’alfonso, Simon
%A Conway, Mike
%Y Zirikly, Aya
%Y Bar, Kfir
%Y MacAvaney, Sean
%Y Ireland, Molly
%Y Ophir, Yaakov
%Y Atzil-Slonim, Dana
%Y Varadarajan, Vasudha
%Y Bedrick, Steven
%Y Desmet, Bart
%S Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-421-7
%F cui-etal-2026-measuring
%X Therapist fidelity and competence rating scales provide a way to measure quality assurance and therapist training outcomes. Scores on these scales reflect the extent to which a therapist adheres to specific therapeutic principles during a psychotherapy session. Existing research has employed natural language processing (NLP) techniques to automatically predict scale ratings. However, existing approaches require a model trained on a dataset of therapy sessions annotated with the target rating scale.Recent work has explored directly inferring therapeutic alliance by computing semantic similarity between therapy transcripts and the Working Alliance Inventory, via cosine similarity between sentence embeddings.In this paper, we extend this line of work by computing semantic similarity between therapist talk turns and therapist fidelity scale items to directly infer fidelity to specific therapeutic modalities. We further enhance this method by augmentation with LLM-generated example therapist utterances that instantiate target behaviours (as expressed by scale items) across varied therapeutic contexts.In evaluations on two independent datasets, our example-augmented semantic similarity approach consistently shows effectiveness in discriminating therapeutic modalities and levels of therapist fidelity.
%U https://aclanthology.org/2026.clpsych-1.22/
%P 271-281
Markdown (Informal)
[Measuring the quality of therapy sessions against assessment scales using augmented semantic-similarity approaches](https://aclanthology.org/2026.clpsych-1.22/) (Cui et al., CLPsych 2026)
ACL