On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914947550674944 |
|---|---|
| author | Li, Huahang Feng, Longyu Li, Shuangyin Hao, Fei Zhang, Chen Jason Song, Yuanfeng |
| author_facet | Li, Huahang Feng, Longyu Li, Shuangyin Hao, Fei Zhang, Chen Jason Song, Yuanfeng |
| contents | Entity resolution, the task of identifying and merging records that refer to the same real-world entity, is crucial in sectors like e-commerce, healthcare, and law enforcement. Large Language Models (LLMs) introduce an innovative approach to this task, capitalizing on their advanced linguistic capabilities and a ``pay-as-you-go'' model that provides significant advantages to those without extensive data science expertise. However, current LLMs are costly due to per-API request billing. Existing methods often either lack quality or become prohibitively expensive at scale. To address these problems, we propose an uncertainty reduction framework using LLMs to improve entity resolution results. We first initialize possible partitions of the entity cluster, refer to the same entity, and define the uncertainty of the result. Then, we reduce the uncertainty by selecting a few valuable matching questions for LLM verification. Upon receiving the answers, we update the probability distribution of the possible partitions. To further reduce costs, we design an efficient algorithm to judiciously select the most valuable matching pairs to query. Additionally, we create error-tolerant techniques to handle LLM mistakes and a dynamic adjustment method to reach truly correct partitions. Experimental results show that our method is efficient and effective, offering promising applications in real-world tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03426 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach Li, Huahang Feng, Longyu Li, Shuangyin Hao, Fei Zhang, Chen Jason Song, Yuanfeng Computation and Language Artificial Intelligence Entity resolution, the task of identifying and merging records that refer to the same real-world entity, is crucial in sectors like e-commerce, healthcare, and law enforcement. Large Language Models (LLMs) introduce an innovative approach to this task, capitalizing on their advanced linguistic capabilities and a ``pay-as-you-go'' model that provides significant advantages to those without extensive data science expertise. However, current LLMs are costly due to per-API request billing. Existing methods often either lack quality or become prohibitively expensive at scale. To address these problems, we propose an uncertainty reduction framework using LLMs to improve entity resolution results. We first initialize possible partitions of the entity cluster, refer to the same entity, and define the uncertainty of the result. Then, we reduce the uncertainty by selecting a few valuable matching questions for LLM verification. Upon receiving the answers, we update the probability distribution of the possible partitions. To further reduce costs, we design an efficient algorithm to judiciously select the most valuable matching pairs to query. Additionally, we create error-tolerant techniques to handle LLM mistakes and a dynamic adjustment method to reach truly correct partitions. Experimental results show that our method is efficient and effective, offering promising applications in real-world tasks. |
| title | On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2401.03426 |