LLM4PR: Improving Post-Ranking in Search Engine with Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917827402792960 |
|---|---|
| author | Yan, Yang Wang, Yihao Zhang, Chi Hou, Wenyuan Pan, Kang Ren, Xingkai Wu, Zelun Zhai, Zhixin Yu, Enyun Ou, Wenwu Song, Yang |
| author_facet | Yan, Yang Wang, Yihao Zhang, Chi Hou, Wenyuan Pan, Kang Ren, Xingkai Wu, Zelun Zhai, Zhixin Yu, Enyun Ou, Wenwu Song, Yang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01178 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM4PR: Improving Post-Ranking in Search Engine with Large Language Models Yan, Yang Wang, Yihao Zhang, Chi Hou, Wenyuan Pan, Kang Ren, Xingkai Wu, Zelun Zhai, Zhixin Yu, Enyun Ou, Wenwu Song, Yang Information Retrieval 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. |
| title | LLM4PR: Improving Post-Ranking in Search Engine with Large Language Models |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2411.01178 |