Retrieval Augmented Spelling Correction for E-Commerce Applications
This addresses a specific problem for e-commerce platforms needing accurate spelling correction amidst rapidly evolving brand names, representing an incremental improvement by adapting existing RAG and LLM methods to this domain.
The paper tackled the challenge of distinguishing genuine misspellings from novel brand names with unconventional spellings in e-commerce spelling correction, using Retrieval Augmented Generation (RAG) to incorporate product names from a catalog into a fine-tuned LLM, resulting in improvements over a stand-alone LLM as shown through quantitative evaluation and qualitative error analyses.
The rapid introduction of new brand names into everyday language poses a unique challenge for e-commerce spelling correction services, which must distinguish genuine misspellings from novel brand names that use unconventional spelling. We seek to address this challenge via Retrieval Augmented Generation (RAG). On this approach, product names are retrieved from a catalog and incorporated into the context used by a large language model (LLM) that has been fine-tuned to do contextual spelling correction. Through quantitative evaluation and qualitative error analyses, we find improvements in spelling correction utilizing the RAG framework beyond a stand-alone LLM. We also demonstrate the value of additional finetuning of the LLM to incorporate retrieved context.