LLMs Instruct LLMs:An Extraction and Editing Method

arXiv:2403.15736v1 Announce Type: new
Abstract: The interest in updating Large Language Models (LLMs) without retraining from scratch is substantial, yet it comes with some challenges.This is especially true for situations demanding complex reasoning with limited samples, a scenario we refer to as the Paucity-Constrained Complex Reasoning Adaptation for LLMs (PCRA-LLM).Traditional methods like Low-Rank Adaptation (LoRA) and Retrieval-Augmented Generation (RAG) are inadequate for this critical issue, particularly evident in our exploration of a specific medical context that epitomize the PCRA-LLM's distinct …

abstract arxiv challenges cs.cl editing extraction language language models large language large language models llm llms low reasoning retraining samples scratch true type