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

2025-08-05

AI Summary

To address high cognitive load and low interaction efficiency in conversational programming caused by misalignment between non-expert users’ intentions and generated code, this paper proposes a novel “Direct Intent–Task Matching” paradigm. Methodologically, it introduces (1) a bidirectional intent alignment mechanism that externalizes and visualizes the LLM’s interpretation of user intent alongside its mapped coding task; (2) a knowledge distillation pipeline that explicitly extracts and represents intent–task associations; and (3) real-time user inspection and editing of these mappings. A user study (N=12) demonstrates that the approach significantly improves intent–task alignment (+42%), reduces cognitive load (p<0.01), and shortens average task completion time by 27%. These results validate the paradigm’s effectiveness in enhancing usability and fidelity in human–LLM collaborative programming for non-programmers.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Intelligent User Interfaces

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Misalignment between user intent and generated code
• Bidirectional ambiguity in nonlinear intents and coding tasks
• Need for direct manipulation of LLM understanding

Innovation

• Direct intent-task matching for human-LLM interaction
• Knowledge distillation extracts LLM understanding and mappings
• Visualizations enable intuitive inspection and editing