NDCG
PulseAugur coverage of NDCG — every cluster mentioning NDCG across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
RAG systems adapt retrieval depth via query clustering for improved accuracy
Researchers have developed a novel framework for adaptive retrieval depth in retrieval-augmented generation (RAG) systems. This approach addresses the limitations of fixed top-k document retrieval by dynamically adjusti…
-
Spruce system enhances private outsourced retrieval for RAG
A new research paper introduces Spruce, a system designed to enhance the privacy and scalability of outsourced retrieval for retrieval-augmented generation (RAG). Spruce achieves significant speedups, up to 22.9x faster…
-
Autonomous agents significantly boost recommender system performance and reveal evaluation flaws · 2 sources tracked
Two new research papers explore the use of autonomous agents in improving recommender systems. The first paper, RecEvolve, details an agent system that autonomously managed the entire research lifecycle for a production…
-
New metric RDQ evaluates multi-answer retrieval systems
Researchers have introduced a new evaluation metric called Rank-Deviation Quality (RDQ) designed for retrieval and ranking systems. RDQ is adaptable to queries with varying numbers of correct answers, from a single resu…
-
New research tackles carousel recommendation evaluation challenges · 2 sources tracked
Two new research papers submitted to arXiv address the challenges of evaluating recommendation systems within carousel interfaces. The first paper focuses on developing a click modeling framework that accounts for the u…
-
Evaluating RAG Systems: Metrics and Layered Harnesses
This article discusses practical methods for evaluating Retrieval-Augmented Generation (RAG) systems, moving beyond subjective assessments. It highlights the importance of separating retrieval failures from generation f…
-
New Expert-Following Strategy Improves Financial Asset Recommendations
Researchers have introduced a new framework called Expert-Following Strategies for financial asset recommendation systems. This approach aims to overcome the trade-off between maximizing investment returns (ROI) and ens…
-
Retrieval Evaluation Metrics Explained: P@K, MRR, NDCG
This article explains key retrieval evaluation metrics used to assess the performance of retrieval systems, including Precision@K (P@K), Recall@k, Mean Reciprocal Rank (MRR), and Normalized Discounted Cumulative Gain (N…
-
Self-EvolveRec framework enhances recommender systems with LLM feedback
Researchers have developed Self-EvolveRec, a new framework designed to improve recommender systems by addressing limitations in traditional design methods. Unlike existing approaches that rely on fixed search spaces or …
-
New SCOReD framework optimizes CoT distillation for recommendation models
Researchers have developed a new framework called SCOReD (Student-Aware CoT Optimization for Recommendation Distillation) to improve the training of smaller language models for recommendation systems. This method optimi…
-
New SCOReD framework optimizes LLM reasoning traces for recommendation systems
Researchers have developed a new framework called SCOReD (Student-Aware CoT Optimization for Recommendation Distillation) to improve the efficiency and effectiveness of training smaller language models (students) using …
-
Enhancing RAG Accuracy with Hybrid Search and Performance Metrics
This article explores techniques to enhance the accuracy of Retrieval-Augmented Generation (RAG) systems, focusing on improving the retrieval of relevant chunks. It details methods such as hybrid search, which combines …
-
New survival analysis method boosts organ allocation efficiency
Researchers have developed a new decision-focused learning approach for survival analysis, aiming to better align predictive models with their downstream allocation tasks. This method optimizes for Normalized Discounted…
-
Researchers explore Query Performance Prediction for optimizing RAG pipelines
Researchers have explored using Query Performance Prediction (QPP) to optimize Retrieval-Augmented Generation (RAG) pipelines by selecting the most effective query variant. This approach aims to reduce computational cos…
-
Recommender systems should prioritize serendipity over pure accuracy for user engagement.
Accuracy is not the sole metric for evaluating recommender systems, as serendipity—the ability to pleasantly surprise users—is also crucial for long-term engagement. While accuracy metrics like NDCG and MAP are widely a…