Relevance Scoring, Learning to Rank, Query Understanding, Result Quality
Personas within Parameters: Fine-Tuning Small Language Models with Low-Rank Adapters to Mimic User Behaviors
arxiv.org·1d
The $350B Shake-Up: How AI Summaries Rewire Publisher Traffic
madcornishprojectionist.co.uk·1d
Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking
arxiv.org·9h
SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
arxiv.org·9h
HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
arxiv.org·1d
Text-to-SQL Oriented to the Process Mining Domain: A PT-EN Dataset for Query Translation
arxiv.org·1d
Loading...Loading more...