LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911925664743424 |
|---|---|
| author | Fang, Chenhao Li, Xiaohan Fan, Zezhong Xu, Jianpeng Nag, Kaushiki Korpeoglu, Evren Kumar, Sushant Achan, Kannan |
| author_facet | Fang, Chenhao Li, Xiaohan Fan, Zezhong Xu, Jianpeng Nag, Kaushiki Korpeoglu, Evren Kumar, Sushant Achan, Kannan |
| contents | Product attribute value extraction is a pivotal component in Natural Language Processing (NLP) and the contemporary e-commerce industry. The provision of precise product attribute values is fundamental in ensuring high-quality recommendations and enhancing customer satisfaction. The recently emerging Large Language Models (LLMs) have demonstrated state-of-the-art performance in numerous attribute extraction tasks, without the need for domain-specific training data. Nevertheless, varying strengths and weaknesses are exhibited by different LLMs due to the diversity in data, architectures, and hyperparameters. This variation makes them complementary to each other, with no single LLM dominating all others. Considering the diverse strengths and weaknesses of LLMs, it becomes necessary to develop an ensemble method that leverages their complementary potentials. In this paper, we propose a novel algorithm called LLM-ensemble to ensemble different LLMs' outputs for attribute value extraction. We iteratively learn the weights for different LLMs to aggregate the labels with weights to predict the final attribute value. Not only can our proposed method be proven theoretically optimal, but it also ensures efficient computation, fast convergence, and safe deployment. We have also conducted extensive experiments with various state-of-the-art LLMs, including Llama2-13B, Llama2-70B, PaLM-2, GPT-3.5, and GPT-4, on Walmart's internal data. Our offline metrics demonstrate that the LLM-ensemble method outperforms all the state-of-the-art single LLMs on Walmart's internal dataset. This method has been launched in several production models, leading to improved Gross Merchandise Volume (GMV), Click-Through Rate (CTR), Conversion Rate (CVR), and Add-to-Cart Rate (ATC). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_00863 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction Fang, Chenhao Li, Xiaohan Fan, Zezhong Xu, Jianpeng Nag, Kaushiki Korpeoglu, Evren Kumar, Sushant Achan, Kannan Information Retrieval Artificial Intelligence Computation and Language Product attribute value extraction is a pivotal component in Natural Language Processing (NLP) and the contemporary e-commerce industry. The provision of precise product attribute values is fundamental in ensuring high-quality recommendations and enhancing customer satisfaction. The recently emerging Large Language Models (LLMs) have demonstrated state-of-the-art performance in numerous attribute extraction tasks, without the need for domain-specific training data. Nevertheless, varying strengths and weaknesses are exhibited by different LLMs due to the diversity in data, architectures, and hyperparameters. This variation makes them complementary to each other, with no single LLM dominating all others. Considering the diverse strengths and weaknesses of LLMs, it becomes necessary to develop an ensemble method that leverages their complementary potentials. In this paper, we propose a novel algorithm called LLM-ensemble to ensemble different LLMs' outputs for attribute value extraction. We iteratively learn the weights for different LLMs to aggregate the labels with weights to predict the final attribute value. Not only can our proposed method be proven theoretically optimal, but it also ensures efficient computation, fast convergence, and safe deployment. We have also conducted extensive experiments with various state-of-the-art LLMs, including Llama2-13B, Llama2-70B, PaLM-2, GPT-3.5, and GPT-4, on Walmart's internal data. Our offline metrics demonstrate that the LLM-ensemble method outperforms all the state-of-the-art single LLMs on Walmart's internal dataset. This method has been launched in several production models, leading to improved Gross Merchandise Volume (GMV), Click-Through Rate (CTR), Conversion Rate (CVR), and Add-to-Cart Rate (ATC). |
| title | LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction |
| topic | Information Retrieval Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2403.00863 |