Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications

2025/06/25 by Xinye Tang, Haijun Zhai, Tang, Xinye +8 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Context-Aware Activity Recognition Systems #Data Stream Mining Techniques #Expert system #FOS: Computer and information sciences #Knowledge base #Process (computing) #Quality (philosophy) #Rank (graph theory) #Ranking (information retrieval) #Recommender Systems and Techniques #Recommender system

paper · pdf · doi:10.48550/arxiv.2506.20815

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/06/25 · openalex created_date 2025/10/15 · openalex updated_date 2026/08/05

Abstract

LLM-powered applications are highly susceptible to the quality of user prompts, and crafting high-quality prompts can often be challenging especially for domain-specific applications. This paper presents a novel dynamic context-aware prompt recommendation system for domain-specific AI applications. Our solution combines contextual query analysis, retrieval-augmented knowledge grounding, hierarchical skill organization, and adaptive skill ranking to generate relevant and actionable prompt suggestions. The system leverages behavioral telemetry and a two-stage hierarchical reasoning process to dynamically select and rank relevant skills, and synthesizes prompts using both predefined and adaptive templates enhanced with few-shot learning. Experiments on real-world datasets demonstrate that our approach achieves high usefulness and relevance, as validated by both automated and expert evaluations.

Citations

• Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task
• MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL
• The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
• Large Language Models
• Efficient Prompting via Dynamic In-Context Learning
• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
• The Power of Scale for Parameter-Efficient Prompt Tuning
• Calibrate Before Use: Improving Few-Shot Performance of Language Models
• User Memory Reasoning for Conversational Recommendation
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Towards Deep Conversational Recommendations

Cited by

• DPCheatSheet: Using Worked and Erroneous LLM-usage Examples to Scaffold Differential Privacy Implementation
• PromptHelper: A Prompt Recommender System for Encouraging Creativity in AI Chatbot Interactions
• ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues

Related

• Instructional Prompt Optimization for Few-Shot LLM-Based Recommendations on Cold-Start Users
• AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
• Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation
• MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs
• Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation