Multi-Layer Ranking with Large Language Models for News Source Recommendation
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_ | 1866913393642831872 |
|---|---|
| author | Zhang, Wenjia Gui, Lin Procter, Rob He, Yulan |
| author_facet | Zhang, Wenjia Gui, Lin Procter, Rob He, Yulan |
| contents | To seek reliable information sources for news events, we introduce a novel task of expert recommendation, which aims to identify trustworthy sources based on their previously quoted statements. To achieve this, we built a novel dataset, called NewsQuote, consisting of 23,571 quote-speaker pairs sourced from a collection of news articles. We formulate the recommendation task as the retrieval of experts based on their likelihood of being associated with a given query. We also propose a multi-layer ranking framework employing Large Language Models to improve the recommendation performance. Our results show that employing an in-context learning based LLM ranker and a multi-layer ranking-based filter significantly improve both the predictive quality and behavioural quality of the recommender system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11745 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Layer Ranking with Large Language Models for News Source Recommendation Zhang, Wenjia Gui, Lin Procter, Rob He, Yulan Information Retrieval Computation and Language To seek reliable information sources for news events, we introduce a novel task of expert recommendation, which aims to identify trustworthy sources based on their previously quoted statements. To achieve this, we built a novel dataset, called NewsQuote, consisting of 23,571 quote-speaker pairs sourced from a collection of news articles. We formulate the recommendation task as the retrieval of experts based on their likelihood of being associated with a given query. We also propose a multi-layer ranking framework employing Large Language Models to improve the recommendation performance. Our results show that employing an in-context learning based LLM ranker and a multi-layer ranking-based filter significantly improve both the predictive quality and behavioural quality of the recommender system. |
| title | Multi-Layer Ranking with Large Language Models for News Source Recommendation |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2406.11745 |