Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2502.14660 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909503063064576 |
|---|---|
| author | Katz, Gali Sitton, Hai Gonen, Guy Kaplan, Yohay |
| author_facet | Katz, Gali Sitton, Hai Gonen, Guy Kaplan, Yohay |
| contents | News recommendation systems personalize homepage content to boost engagement, but factors like content type, editorial stance, and geographic focus impact recommendations. Local newspapers balance coverage across regions, yet identifying local articles is challenging due to implicit location cues like slang or landmarks.
Traditional methods, such as Named Entity Recognition (NER) and Knowledge Graphs, infer locations, but Large Language Models (LLMs) offer new possibilities while raising concerns about accuracy and explainability.
This paper explores LLMs for local article classification in Taboola's "Homepage For You" system, comparing them to traditional techniques. Key findings: (1) Knowledge Graphs enhance NER models' ability to detect implicit locations, (2) LLMs outperform traditional methods, and (3) LLMs can effectively identify local content without requiring Knowledge Graph integration.
Offline evaluations showed LLMs excel at implicit location classification, while online A/B tests showed a significant increased in local views. A scalable pipeline integrating LLM-based location classification boosted local article distribution by 27%, preserving newspapers' brand identity and enhancing homepage personalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14660 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond the Surface: Uncovering Implicit Locations with LLMs for Personalized Local News Katz, Gali Sitton, Hai Gonen, Guy Kaplan, Yohay Machine Learning 68T50 News recommendation systems personalize homepage content to boost engagement, but factors like content type, editorial stance, and geographic focus impact recommendations. Local newspapers balance coverage across regions, yet identifying local articles is challenging due to implicit location cues like slang or landmarks. Traditional methods, such as Named Entity Recognition (NER) and Knowledge Graphs, infer locations, but Large Language Models (LLMs) offer new possibilities while raising concerns about accuracy and explainability. This paper explores LLMs for local article classification in Taboola's "Homepage For You" system, comparing them to traditional techniques. Key findings: (1) Knowledge Graphs enhance NER models' ability to detect implicit locations, (2) LLMs outperform traditional methods, and (3) LLMs can effectively identify local content without requiring Knowledge Graph integration. Offline evaluations showed LLMs excel at implicit location classification, while online A/B tests showed a significant increased in local views. A scalable pipeline integrating LLM-based location classification boosted local article distribution by 27%, preserving newspapers' brand identity and enhancing homepage personalization. |
| title | Beyond the Surface: Uncovering Implicit Locations with LLMs for Personalized Local News |
| topic | Machine Learning 68T50 |
| url | https://arxiv.org/abs/2502.14660 |