Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Wenshuo, Shen, Leixian, Xu, Shuchang, Wang, Jindu, Zhao, Jian, Qu, Huamin, Yuan, Linping
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.02823
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916880687562752
author Zhang, Wenshuo
Shen, Leixian
Xu, Shuchang
Wang, Jindu
Zhao, Jian
Qu, Huamin
Yuan, Linping
author_facet Zhang, Wenshuo
Shen, Leixian
Xu, Shuchang
Wang, Jindu
Zhao, Jian
Qu, Huamin
Yuan, Linping
contents Conversational LLMs have been widely adopted by domain users with limited programming experience to solve domain problems. However, these users often face misalignment between their intent and generated code, resulting in frustration and rounds of clarification. This work first investigates the cause of this misalignment, which dues to bidirectional ambiguity: both user intents and coding tasks are inherently nonlinear, yet must be expressed and interpreted through linear prompts and code sequences. To address this, we propose direct intent-task matching, a new human-LLM interaction paradigm that externalizes and enables direct manipulation of the LLM understanding, i.e., the coding tasks and their relationships inferred by the LLM prior to code generation. As a proof-of-concept, this paradigm is then implemented in NeuroSync, which employs a knowledge distillation pipeline to extract LLM understanding, user intents, and their mappings, and enhances the alignment by allowing users to intuitively inspect and edit them via visualizations. We evaluate the algorithmic components of NeuroSync via technical experiments, and assess its overall usability and effectiveness via a user study (N=12). The results show that it enhances intent-task alignment, lowers cognitive effort, and improves coding efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02823
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification
Zhang, Wenshuo
Shen, Leixian
Xu, Shuchang
Wang, Jindu
Zhao, Jian
Qu, Huamin
Yuan, Linping
Human-Computer Interaction
Artificial Intelligence
Computation and Language
Software Engineering
Conversational LLMs have been widely adopted by domain users with limited programming experience to solve domain problems. However, these users often face misalignment between their intent and generated code, resulting in frustration and rounds of clarification. This work first investigates the cause of this misalignment, which dues to bidirectional ambiguity: both user intents and coding tasks are inherently nonlinear, yet must be expressed and interpreted through linear prompts and code sequences. To address this, we propose direct intent-task matching, a new human-LLM interaction paradigm that externalizes and enables direct manipulation of the LLM understanding, i.e., the coding tasks and their relationships inferred by the LLM prior to code generation. As a proof-of-concept, this paradigm is then implemented in NeuroSync, which employs a knowledge distillation pipeline to extract LLM understanding, user intents, and their mappings, and enhances the alignment by allowing users to intuitively inspect and edit them via visualizations. We evaluate the algorithmic components of NeuroSync via technical experiments, and assess its overall usability and effectiveness via a user study (N=12). The results show that it enhances intent-task alignment, lowers cognitive effort, and improves coding efficiency.
title NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
Software Engineering
url https://arxiv.org/abs/2508.02823