@inproceedings{liu-etal-2026-discerning,
title = "Discerning Minds or Generic Tutors? Evaluating Instructional Guidance Capabilities in Socratic {LLM}s",
author = "Liu, Ying and
Li, Can and
Zhang, Ting and
Wang, Mei and
Zhu, Qiannan and
Li, Jian and
Huang, Hua",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1588/",
pages = "33802--33834",
ISBN = "979-8-89176-462-0",
abstract = "The conversational capabilities of large language models hold significant promise for enabling scalable and interactive tutoring. Prior work has primarily evaluated general instructional competence while overlooking a critical dimension: the ability to adaptively guide learners based on their evolving cognitive states. This study takes instructional guidance as a core capability and asks whether LLMs can emulate expert tutors who dynamically adjust strategies in response to learners' needs. We introduce GuideEval, a benchmark grounded in authentic educational dialogues that evaluates pedagogical guidance through a three-phase behavioral framework: (i) Assessment, inferring learner states; (ii) Orchestration, adapting instructional strategies; and (iii) Elicitation, stimulating proper reflections. Empirical results indicate that existing LLMs often fail to provide effective adaptive scaffolding when learners experience confusion or require redirection. Complementing quantitative results, we present a detailed failure case analysis, offering intuitive insights into these limitations. We further propose a behavior-guided finetuning strategy based on behavior-prompted instructional dialogues, substantially enhancing guidance performance. By shifting the focus from isolated content correctness to learner-centered state-aware interaction, this work advocates a more dialogic paradigm for evaluating Socratic LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-discerning">
<titleInfo>
<title>Discerning Minds or Generic Tutors? Evaluating Instructional Guidance Capabilities in Socratic LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Can</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiannan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>The conversational capabilities of large language models hold significant promise for enabling scalable and interactive tutoring. Prior work has primarily evaluated general instructional competence while overlooking a critical dimension: the ability to adaptively guide learners based on their evolving cognitive states. This study takes instructional guidance as a core capability and asks whether LLMs can emulate expert tutors who dynamically adjust strategies in response to learners’ needs. We introduce GuideEval, a benchmark grounded in authentic educational dialogues that evaluates pedagogical guidance through a three-phase behavioral framework: (i) Assessment, inferring learner states; (ii) Orchestration, adapting instructional strategies; and (iii) Elicitation, stimulating proper reflections. Empirical results indicate that existing LLMs often fail to provide effective adaptive scaffolding when learners experience confusion or require redirection. Complementing quantitative results, we present a detailed failure case analysis, offering intuitive insights into these limitations. We further propose a behavior-guided finetuning strategy based on behavior-prompted instructional dialogues, substantially enhancing guidance performance. By shifting the focus from isolated content correctness to learner-centered state-aware interaction, this work advocates a more dialogic paradigm for evaluating Socratic LLMs.</abstract>
<identifier type="citekey">liu-etal-2026-discerning</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1588/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>33802</start>
<end>33834</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discerning Minds or Generic Tutors? Evaluating Instructional Guidance Capabilities in Socratic LLMs
%A Liu, Ying
%A Li, Can
%A Zhang, Ting
%A Wang, Mei
%A Zhu, Qiannan
%A Li, Jian
%A Huang, Hua
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F liu-etal-2026-discerning
%X The conversational capabilities of large language models hold significant promise for enabling scalable and interactive tutoring. Prior work has primarily evaluated general instructional competence while overlooking a critical dimension: the ability to adaptively guide learners based on their evolving cognitive states. This study takes instructional guidance as a core capability and asks whether LLMs can emulate expert tutors who dynamically adjust strategies in response to learners’ needs. We introduce GuideEval, a benchmark grounded in authentic educational dialogues that evaluates pedagogical guidance through a three-phase behavioral framework: (i) Assessment, inferring learner states; (ii) Orchestration, adapting instructional strategies; and (iii) Elicitation, stimulating proper reflections. Empirical results indicate that existing LLMs often fail to provide effective adaptive scaffolding when learners experience confusion or require redirection. Complementing quantitative results, we present a detailed failure case analysis, offering intuitive insights into these limitations. We further propose a behavior-guided finetuning strategy based on behavior-prompted instructional dialogues, substantially enhancing guidance performance. By shifting the focus from isolated content correctness to learner-centered state-aware interaction, this work advocates a more dialogic paradigm for evaluating Socratic LLMs.
%U https://aclanthology.org/2026.findings-emnlp.1588/
%P 33802-33834
Markdown (Informal)
[Discerning Minds or Generic Tutors? Evaluating Instructional Guidance Capabilities in Socratic LLMs](https://aclanthology.org/2026.findings-emnlp.1588/) (Liu et al., Findings 2026)
ACL