LLM4PR: Improving Post-Ranking in Search Engine with Large Language Models

TL;DR

A novel paradigm named Large Language Models for Post-Ranking in search engine (LLM4PR) is introduced, which leverages the capabilities of LLMs to accomplish the post-ranking task in SE and exhibits state-of-the-art performance compared with other alternatives.

Abstract

Alongside the rapid development of Large Language Models (LLMs), there has been a notable increase in efforts to integrate LLM techniques in information retrieval (IR) and search engines (SE). Recently, an additional post-ranking stage is suggested in SE to enhance user satisfaction in practical applications. Nevertheless, research dedicated to enhancing the post-ranking stage through LLMs remains largely unexplored. In this study, we introduce a novel paradigm named Large Language Models for Post-Ranking in search engine (LLM4PR), which leverages the capabilities of LLMs to accomplish the post-ranking task in SE. Concretely, a Query-Instructed Adapter (QIA) module is designed to derive the user/item representation vectors by incorporating their heterogeneous features. A feature adaptation step is further introduced to align the semantics of user/item representations with the LLM. Finally, the LLM4PR integrates a learning to post-rank step, leveraging both a main task and an auxiliary task to fine-tune the model to adapt the post-ranking task. Experiment studies demonstrate that the proposed framework leads to significant improvements and exhibits state-of-the-art performance compared with other alternatives.

Figures (6)

• Figure 1: Illustration of the search process, encompassing matching, ranking and post-ranking stages.
• Figure 2: Overview of the proposed LLM4PR framework.
• Figure 3: Illustration of the feature adaptation step.
• Figure 4: Illustration of the learning to post-rank step.
• Figure 5: Post-ranking performance comparison w.r.t. different sizes of backbone language models.