Aligning Large Language Models for Controllable Recommendations
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_ | 1866916345582452736 |
|---|---|
| author | Lu, Wensheng Lian, Jianxun Zhang, Wei Li, Guanghua Zhou, Mingyang Liao, Hao Xie, Xing |
| author_facet | Lu, Wensheng Lian, Jianxun Zhang, Wei Li, Guanghua Zhou, Mingyang Liao, Hao Xie, Xing |
| contents | Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems - systems that are conversational, explainable, and controllable. However, existing literature primarily concentrates on integrating domain-specific knowledge into LLMs to enhance accuracy, often neglecting the ability to follow instructions. To address this gap, we initially introduce a collection of supervised learning tasks, augmented with labels derived from a conventional recommender model, aimed at explicitly improving LLMs' proficiency in adhering to recommendation-specific instructions. Subsequently, we develop a reinforcement learning-based alignment procedure to further strengthen LLMs' aptitude in responding to users' intentions and mitigating formatting errors. Through extensive experiments on two real-world datasets, our method markedly advances the capability of LLMs to comply with instructions within recommender systems, while sustaining a high level of accuracy performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05063 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Aligning Large Language Models for Controllable Recommendations Lu, Wensheng Lian, Jianxun Zhang, Wei Li, Guanghua Zhou, Mingyang Liao, Hao Xie, Xing Information Retrieval Artificial Intelligence 68T50 Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems - systems that are conversational, explainable, and controllable. However, existing literature primarily concentrates on integrating domain-specific knowledge into LLMs to enhance accuracy, often neglecting the ability to follow instructions. To address this gap, we initially introduce a collection of supervised learning tasks, augmented with labels derived from a conventional recommender model, aimed at explicitly improving LLMs' proficiency in adhering to recommendation-specific instructions. Subsequently, we develop a reinforcement learning-based alignment procedure to further strengthen LLMs' aptitude in responding to users' intentions and mitigating formatting errors. Through extensive experiments on two real-world datasets, our method markedly advances the capability of LLMs to comply with instructions within recommender systems, while sustaining a high level of accuracy performance. |
| title | Aligning Large Language Models for Controllable Recommendations |
| topic | Information Retrieval Artificial Intelligence 68T50 |
| url | https://arxiv.org/abs/2403.05063 |