BRIGHT

The 'BRIGHT' dataset/benchmark is used to evaluate the effectiveness of text embedding models in retrieval and listwise reranking tasks.

Papers using BRIGHT (3)

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction2026E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker2025Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval2025