MSMARCO

The MSMARCO dataset is a benchmark that contains a collection of question-answer pairs used to evaluate the performance of models in information retrieval and question answering tasks.

Papers using MSMARCO (12)

Can Language Models Actually Retrieve In-Context? Drowning in Documents at Million Token Scale2026LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization2025 · 4 citesEnhancing Metacognitive AI: Knowledge-Graph Population with Graph-Theoretic LLM Enrichment2026Calibrating LLMs with Semantic-level Reward2026Training-Induced Bias Toward LLM-Generated Content in Dense Retrieval2026Scalable In-context Ranking with Generative Models2025Doc2Query++: Topic-Coverage based Document Expansion and its Application to Dense Retrieval via Dual-Index Fusion2025Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion2025Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation2025Scaling Sparse and Dense Retrieval in Decoder-Only LLMs2025Matryoshka Re-Ranker: A Flexible Re-Ranking Architecture With Configurable Depth and Width2025Inference Scaling for Bridging Retrieval and Augmented Generation2024