@inproceedings{he-kim-2026-whose,
title = "Whose Repair? A Multi-Loop Diagnostic of Interactive Alignment in Human{--}{LLM} Conversation",
author = "He, Wanqing Psyche and
Kim, Midam",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.106/",
pages = "1565--1574",
ISBN = "979-8-89176-485-9",
abstract = "Two conversations can end with equally correct answers while requiring unequal user effort. One system may correct its own prior error. Another may succeed only after the user restores an instruction, referent, or evidential standard. Output-focused evaluation can assign these trajectories the same result and overlook who performed the work required for recovery. We propose a framework for measuring this difference through observable repair sequences in conversations between humans and large language models. Extending Pickering and Garrod{'}s Interactive Alignment Model, the framework combines four concurrent functional loops (Grounding, Continuity, Negotiation, and Epistemic) with a structural classification of who initiates and resolves repair and a temporal hypothesis about expectation stabilization. It generates testable predictions about system self-repair, epistemic signaling, and phase-dependent repair cost. In a pilot analysis of 30 dialogues, two human annotators achieved substantial agreement under an earlier turn-level rubric (Cohen{'}s {\ensuremath{\kappa}} = .75). The analysis revealed category-boundary problems that motivate the revised sequence-level framework presented here. Its evidential scope is limited to annotation feasibility. The resulting account makes repair burden measurable and specifies the evidence required for future validation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-kim-2026-whose">
<titleInfo>
<title>Whose Repair? A Multi-Loop Diagnostic of Interactive Alignment in Human–LLM Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanqing</namePart>
<namePart type="given">Psyche</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Midam</namePart>
<namePart type="family">Kim</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>Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</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">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>Two conversations can end with equally correct answers while requiring unequal user effort. One system may correct its own prior error. Another may succeed only after the user restores an instruction, referent, or evidential standard. Output-focused evaluation can assign these trajectories the same result and overlook who performed the work required for recovery. We propose a framework for measuring this difference through observable repair sequences in conversations between humans and large language models. Extending Pickering and Garrod’s Interactive Alignment Model, the framework combines four concurrent functional loops (Grounding, Continuity, Negotiation, and Epistemic) with a structural classification of who initiates and resolves repair and a temporal hypothesis about expectation stabilization. It generates testable predictions about system self-repair, epistemic signaling, and phase-dependent repair cost. In a pilot analysis of 30 dialogues, two human annotators achieved substantial agreement under an earlier turn-level rubric (Cohen’s \ensuremathąppa = .75). The analysis revealed category-boundary problems that motivate the revised sequence-level framework presented here. Its evidential scope is limited to annotation feasibility. The resulting account makes repair burden measurable and specifies the evidence required for future validation.</abstract>
<identifier type="citekey">he-kim-2026-whose</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.106/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1565</start>
<end>1574</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Whose Repair? A Multi-Loop Diagnostic of Interactive Alignment in Human–LLM Conversation
%A He, Wanqing Psyche
%A Kim, Midam
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F he-kim-2026-whose
%X Two conversations can end with equally correct answers while requiring unequal user effort. One system may correct its own prior error. Another may succeed only after the user restores an instruction, referent, or evidential standard. Output-focused evaluation can assign these trajectories the same result and overlook who performed the work required for recovery. We propose a framework for measuring this difference through observable repair sequences in conversations between humans and large language models. Extending Pickering and Garrod’s Interactive Alignment Model, the framework combines four concurrent functional loops (Grounding, Continuity, Negotiation, and Epistemic) with a structural classification of who initiates and resolves repair and a temporal hypothesis about expectation stabilization. It generates testable predictions about system self-repair, epistemic signaling, and phase-dependent repair cost. In a pilot analysis of 30 dialogues, two human annotators achieved substantial agreement under an earlier turn-level rubric (Cohen’s \ensuremathąppa = .75). The analysis revealed category-boundary problems that motivate the revised sequence-level framework presented here. Its evidential scope is limited to annotation feasibility. The resulting account makes repair burden measurable and specifies the evidence required for future validation.
%U https://aclanthology.org/2026.realm-1.106/
%P 1565-1574
Markdown (Informal)
[Whose Repair? A Multi-Loop Diagnostic of Interactive Alignment in Human–LLM Conversation](https://aclanthology.org/2026.realm-1.106/) (He & Kim, REALM 2026)
ACL