Similar Data Points Identification with LLM: A Human-in-the-loop Strategy Using Summarization and Hidden State Insights

arXiv:2404.04281v1 Announce Type: new
Abstract: This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point summarization and hidden state extraction. Initially, data is condensed via summarization using an LLM, reducing complexity and highlighting essential information in sentences. Subsequently, the summarization sentences are fed through another LLM to extract hidden states, serving as compact, feature-rich representations. This …

abstract arxiv cs.ai cs.cl data domains extraction free hidden human identification image image data insights language language models large language large language models llm llms loop simple state strategy study summarization tabular text type