Researchers have developed LLM4AIGQ, a new framework that uses large language models to generate AI guidance queries for e-commerce. This system aims to improve upon traditional methods by segmenting user interests and inferring specific consumption intents for each, leading to more valuable guidance queries. The framework is trained using a pipeline of Supervised Fine-Tuning (SFT), Reinforcement Learning (RL), and Direct Preference Optimization (DPO), incorporating a multi-level reward design for complex optimization tasks. LLM4AIGQ is designed for nearline generation and online reading to meet latency requirements, and has shown strong performance in both offline evaluations and online A/B tests. AI
IMPACT This framework could enhance e-commerce personalization and improve user engagement by generating more relevant search queries.
RANK_REASON The cluster contains a research paper detailing a new framework for AI guidance query generation. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
- AIGQ
- AI Guidance Query Generation
- Direct Preference Optimization
- LLM4AIGQ
- Q2AIGQ
- reinforcement learning
- supervised fine-tuning
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
