Disambiguate Entity Matching using Large Language Models through Relation Discovery
This addresses a core challenge in data integration and cleaning for analysts dealing with ambiguous entity definitions, though it appears incremental by building on existing LLM methods.
The paper tackles the problem of entity matching ambiguity in data integration by shifting focus from semantic similarity to understanding relations between entities, proposing a novel approach that allows analysts to navigate similarity spectrums more effectively.
Entity matching is a critical challenge in data integration and cleaning, central to tasks like fuzzy joins and deduplication. Traditional approaches have focused on overcoming fuzzy term representations through methods such as edit distance, Jaccard similarity, and more recently, embeddings and deep neural networks, including advancements from large language models (LLMs) like GPT. However, the core challenge in entity matching extends beyond term fuzziness to the ambiguity in defining what constitutes a "match," especially when integrating with external databases. This ambiguity arises due to varying levels of detail and granularity among entities, complicating exact matches. We propose a novel approach that shifts focus from purely identifying semantic similarities to understanding and defining the "relations" between entities as crucial for resolving ambiguities in matching. By predefining a set of relations relevant to the task at hand, our method allows analysts to navigate the spectrum of similarity more effectively, from exact matches to conceptually related entities.