@inproceedings{madani-srihari-2025-esc,
title = "{ESC}-Judge: A Framework for Comparing Emotional Support Conversational Agents",
author = "Madani, Navid and
Srihari, Rohini",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.811/",
pages = "16059--16076",
ISBN = "979-8-89176-332-6",
abstract = "Large Language Models (LLMs) increasingly power mental-health chatbots, yet the field still lacks a scalable, theory-grounded way to decide which model is more effective to deploy. We present ESC-Judge, the first end-to-end evaluation framework that (i) grounds head-to-head comparison of Emotional-Support LLMs (ES-LLMs) in an established psychological theory{---}Clara Hill{'}s Exploration{--}Insight{--}Action (E-I-A) counselling model{---}thereby delivering a structured, interpretable lens on performance, and (ii) fully automates the pipeline at scale. ESC-Judge proceeds in three stages: (1) it synthesizes realistic help-seeker roles by sampling empirically salient attributes (stressors, personality, life history); (2) it has two candidate ES-Agents conduct separate sessions with the same role, isolating model-specific strategies; and (3) it asks a specialised judge LLM to issue pairwise preferences across rubric-anchored skills that exhaustively cover the E-I-A spectrum. In our empirical study, ESC-Judge matches PhD-level annotators in 85{\%} of Exploration, 83{\%} of Insight, and 86{\%} of Action decisions, demonstrating human-level reliability at a fraction of the cost. We release all code, prompts, synthetic roles, transcripts, and judgment scripts to catalyze transparent progress in emotionally supportive AI"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="madani-srihari-2025-esc">
<titleInfo>
<title>ESC-Judge: A Framework for Comparing Emotional Support Conversational Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Navid</namePart>
<namePart type="family">Madani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohini</namePart>
<namePart type="family">Srihari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) increasingly power mental-health chatbots, yet the field still lacks a scalable, theory-grounded way to decide which model is more effective to deploy. We present ESC-Judge, the first end-to-end evaluation framework that (i) grounds head-to-head comparison of Emotional-Support LLMs (ES-LLMs) in an established psychological theory—Clara Hill’s Exploration–Insight–Action (E-I-A) counselling model—thereby delivering a structured, interpretable lens on performance, and (ii) fully automates the pipeline at scale. ESC-Judge proceeds in three stages: (1) it synthesizes realistic help-seeker roles by sampling empirically salient attributes (stressors, personality, life history); (2) it has two candidate ES-Agents conduct separate sessions with the same role, isolating model-specific strategies; and (3) it asks a specialised judge LLM to issue pairwise preferences across rubric-anchored skills that exhaustively cover the E-I-A spectrum. In our empirical study, ESC-Judge matches PhD-level annotators in 85% of Exploration, 83% of Insight, and 86% of Action decisions, demonstrating human-level reliability at a fraction of the cost. We release all code, prompts, synthetic roles, transcripts, and judgment scripts to catalyze transparent progress in emotionally supportive AI</abstract>
<identifier type="citekey">madani-srihari-2025-esc</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.811/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>16059</start>
<end>16076</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ESC-Judge: A Framework for Comparing Emotional Support Conversational Agents
%A Madani, Navid
%A Srihari, Rohini
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F madani-srihari-2025-esc
%X Large Language Models (LLMs) increasingly power mental-health chatbots, yet the field still lacks a scalable, theory-grounded way to decide which model is more effective to deploy. We present ESC-Judge, the first end-to-end evaluation framework that (i) grounds head-to-head comparison of Emotional-Support LLMs (ES-LLMs) in an established psychological theory—Clara Hill’s Exploration–Insight–Action (E-I-A) counselling model—thereby delivering a structured, interpretable lens on performance, and (ii) fully automates the pipeline at scale. ESC-Judge proceeds in three stages: (1) it synthesizes realistic help-seeker roles by sampling empirically salient attributes (stressors, personality, life history); (2) it has two candidate ES-Agents conduct separate sessions with the same role, isolating model-specific strategies; and (3) it asks a specialised judge LLM to issue pairwise preferences across rubric-anchored skills that exhaustively cover the E-I-A spectrum. In our empirical study, ESC-Judge matches PhD-level annotators in 85% of Exploration, 83% of Insight, and 86% of Action decisions, demonstrating human-level reliability at a fraction of the cost. We release all code, prompts, synthetic roles, transcripts, and judgment scripts to catalyze transparent progress in emotionally supportive AI
%U https://aclanthology.org/2025.emnlp-main.811/
%P 16059-16076
Markdown (Informal)
[ESC-Judge: A Framework for Comparing Emotional Support Conversational Agents](https://aclanthology.org/2025.emnlp-main.811/) (Madani & Srihari, EMNLP 2025)
ACL