NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification

TL;DR

NeuroSync introduces a new interaction paradigm for LLMs that externalizes and allows direct editing of the model's understanding of coding tasks, improving alignment and efficiency for users with limited programming experience.

Contribution

This work proposes direct intent-task matching and implements NeuroSync, a system that externalizes LLM understanding and enables user manipulation to improve code generation alignment.

Findings

Enhanced intent-task alignment observed

Reduced user cognitive effort

Improved coding efficiency

Abstract

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.