TRAWL: External Knowledge-Enhanced Recommendation with LLM Assistance
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_ | 1866911885482262528 |
|---|---|
| author | Luo, Weiqing Song, Chonggang Yi, Lingling Cheng, Gong |
| author_facet | Luo, Weiqing Song, Chonggang Yi, Lingling Cheng, Gong |
| contents | Combining semantic information with behavioral data is a crucial research area in recommender systems. A promising approach involves leveraging external knowledge to enrich behavioral-based recommender systems with abundant semantic information. However, this approach faces two primary challenges: denoising raw external knowledge and adapting semantic representations. To address these challenges, we propose an External Knowledge-Enhanced Recommendation method with LLM Assistance (TRAWL). This method utilizes large language models (LLMs) to extract relevant recommendation knowledge from raw external data and employs a contrastive learning strategy for adapter training. Experiments on public datasets and real-world online recommender systems validate the effectiveness of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06642 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TRAWL: External Knowledge-Enhanced Recommendation with LLM Assistance Luo, Weiqing Song, Chonggang Yi, Lingling Cheng, Gong Information Retrieval Artificial Intelligence Computation and Language Combining semantic information with behavioral data is a crucial research area in recommender systems. A promising approach involves leveraging external knowledge to enrich behavioral-based recommender systems with abundant semantic information. However, this approach faces two primary challenges: denoising raw external knowledge and adapting semantic representations. To address these challenges, we propose an External Knowledge-Enhanced Recommendation method with LLM Assistance (TRAWL). This method utilizes large language models (LLMs) to extract relevant recommendation knowledge from raw external data and employs a contrastive learning strategy for adapter training. Experiments on public datasets and real-world online recommender systems validate the effectiveness of our approach. |
| title | TRAWL: External Knowledge-Enhanced Recommendation with LLM Assistance |
| topic | Information Retrieval Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2403.06642 |