Generating Search Explanations using Large Language Models

TL;DR

This paper explores using large language models to generate explanations for search results, demonstrating that LLMs produce more accurate and plausible explanations than baseline models.

Contribution

It introduces a novel application of LLMs for search explanations, showing their effectiveness over existing baseline methods.

Findings

LLMs generate more accurate explanations than baselines.

Explanations are more plausible and user-friendly.

The approach improves user understanding of search results.

Abstract

Aspect-oriented explanations in search results are typically concise text snippets placed alongside retrieved documents to serve as explanations that assist users in efficiently locating relevant information. While Large Language Models (LLMs) have demonstrated exceptional performance for a range of problems, their potential to generate explanations for search results has not been explored. This study addresses that gap by leveraging both encoder-decoder and decoder-only LLMs to generate explanations for search results. The explanations generated are consistently more accurate and plausible explanations than those produced by a range of baseline models.