Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking
MERIT-Rank integrates multiple LLM reasoning trajectories for text reranking; its 4B model outperforms most 7B and 32B rerankers on BRIGHT.
1 stories, newest first · one card per story
MERIT-Rank integrates multiple LLM reasoning trajectories for text reranking; its 4B model outperforms most 7B and 32B rerankers on BRIGHT.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views