Search Results for author:
Found 2 papers, 2 papers with code
ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMs
ExaRanker recently introduced an approach to training information retrieval (IR) models, incorporating natural language explanations as additional labels.
ExaRanker: Explanation-Augmented Neural Ranker
Recent work has shown that inducing a large language model (LLM) to generate explanations prior to outputting an answer is an effective strategy to improve performance on a wide range of reasoning tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
