Beyond Turns: Fragment-Response Alignment for Evolving Intent and Traceable Review in LLM Chat

Xichun Xu; Ruofei Du; Jiaqi Zheng; Lijie Yao; Liu YANG; Qingping Wang

Beyond Turns: Fragment-Response Alignment for Evolving Intent and Traceable Review in LLM Chat

Xichun Xu
, Ruofei Du
, Jiaqi Zheng
, Lijie Yao
, Liu YANG^*
, Qingping Wang

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

Abstract

LLM chat interfaces are increasingly used for complex tasks, yet remain tethered to rigid, chronological transcripts. This structure creates a "traceability gap," hindering users from mapping evolving intent to fragmented model outputs. In this work, we introduce Fragment-Response Alignment, a conceptual framework that maps user intent fragments to specific AI response units. We report findings from a formative study of 16 participants, which reveal three core phenomena: intent is continuously evolving, interaction functions as a traceability reconstruction task, and users naturally employ fragment-based mental models.

Original language	English
Publication status	Accepted/In press - Nov 2026

Cite this

@conference{29b16124c3904f59b6d1713a928736de,

title = "Beyond Turns: Fragment-Response Alignment for Evolving Intent and Traceable Review in LLM Chat",

abstract = "LLM chat interfaces are increasingly used for complex tasks, yet remain tethered to rigid, chronological transcripts. This structure creates a {"}traceability gap,{"} hindering users from mapping evolving intent to fragmented model outputs. In this work, we introduce Fragment-Response Alignment, a conceptual framework that maps user intent fragments to specific AI response units. We report findings from a formative study of 16 participants, which reveal three core phenomena: intent is continuously evolving, interaction functions as a traceability reconstruction task, and users naturally employ fragment-based mental models.",

author = "Xichun Xu and Ruofei Du and Jiaqi Zheng and Lijie Yao and Liu YANG and Qingping Wang",

year = "2026",

month = nov,

language = "English",

}

TY - CONF

T1 - Beyond Turns: Fragment-Response Alignment for Evolving Intent and Traceable Review in LLM Chat

AU - Xu, Xichun

AU - Du, Ruofei

AU - Zheng, Jiaqi

AU - Yao, Lijie

AU - YANG, Liu

AU - Wang, Qingping

PY - 2026/11

Y1 - 2026/11

N2 - LLM chat interfaces are increasingly used for complex tasks, yet remain tethered to rigid, chronological transcripts. This structure creates a "traceability gap," hindering users from mapping evolving intent to fragmented model outputs. In this work, we introduce Fragment-Response Alignment, a conceptual framework that maps user intent fragments to specific AI response units. We report findings from a formative study of 16 participants, which reveal three core phenomena: intent is continuously evolving, interaction functions as a traceability reconstruction task, and users naturally employ fragment-based mental models.

AB - LLM chat interfaces are increasingly used for complex tasks, yet remain tethered to rigid, chronological transcripts. This structure creates a "traceability gap," hindering users from mapping evolving intent to fragmented model outputs. In this work, we introduce Fragment-Response Alignment, a conceptual framework that maps user intent fragments to specific AI response units. We report findings from a formative study of 16 participants, which reveal three core phenomena: intent is continuously evolving, interaction functions as a traceability reconstruction task, and users naturally employ fragment-based mental models.

M3 - Paper

ER -