Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models
Information extraction (IE) plays a crucial role in natural language processing (NLP) by converting unstructured text into structured knowledge. Deploying computationally intensive large language models (LLMs) on resource-constrained devices for information extraction is challenging, particularly due to issues like hallucinations, limited context length, and high latency-especially when handling diverse extraction schemas. To address these challenges, we propose a two-stage information extraction approach adapted for on-device LLMs, called Dual-LoRA with Incremental Schema Caching (DLISC), which enhances both schema identification and schema-aware extraction in terms of effectiveness and efficiency. In particular, DLISC adopts an Identification LoRA module for retrieving the most relevant schemas to a given query, and an Extraction LoRA module for performing information extraction based on the previously selected schemas. To accelerate extraction inference, Incremental Schema Caching is incorporated to reduce redundant computation, substantially improving efficiency. Extensive experiments across multiple information extraction datasets demonstrate notable improvements in both effectiveness and efficiency.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation
Event extraction (EE) is a fundamental task in natural language processing (NLP) that involves identifying and extracting event information from unstructured text. Effective EE in real-world scenarios requires two key st…
Event ExtractionHallucinationRetrievalRetrieval-augmented GenerationEnhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis
Key Information Extraction (KIE) converts visually rich documents into structured data, but practical deployment remains challenging: strong performance often relies on costly on-server Large Multimodal Models (LMMs), wh…
Key Information ExtractionChatSchema: A pipeline of extracting structured information with Large Multimodal Models based on schema
Objective: This study introduces ChatSchema, an effective method for extracting and structuring information from unstructured data in medical paper reports using a combination of Large Multimodal Models (LMMs) and Optica…
Optical Character RecognitionOptical Character Recognition (OCR)DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering
Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Language Models (LLMs) and Retrieval-Augmente…
Information ExtractionRelational ReasoningQuestion AnsweringA Graphical Interface for Curating Schemas
Much past work has focused on extracting information like events, entities, and relations from documents. Very little work has focused on analyzing these results for better model understanding. In this paper, we introduc…