애스크로AIPublic Preview
← 학술논문 검색
학술논문멀티미디어학회논문지2026.03 발행

소형 LLM을 활용한 강조표기 기반 특허 차이점 식별

Emphasis-Based Extraction of Patent Differences Using Small Language Model

이현진(한국특허정보원); 고봉수(한국특허정보원); 박진우(한국특허정보원); 이봉건(한국특허정보원)

29권 3호, 593~600쪽

초록

This study investigates the extraction of differences unique to the application invention using small LLMs under resource-constrained environments. Given technically similar invention pairs annotated with emphasis markers(**), the task is explicitly defined as selectively identifying only those differences that are emphasized and unique to the Application Invention. We compare Baseline, Prompt Engineering, and Fine-tuning approaches using Qwen2.5-14B. Experimental results show that Prompt Engineering and Fine-tuning outperform the Baseline, with the fine-tuned small model slightly exceeding the baseline performance of GPT-OSS-120B, indicating that task-specific adaptation can offset model scale limitations.

Abstract

This study investigates the extraction of differences unique to the application invention using small LLMs under resource-constrained environments. Given technically similar invention pairs annotated with emphasis markers(**), the task is explicitly defined as selectively identifying only those differences that are emphasized and unique to the Application Invention. We compare Baseline, Prompt Engineering, and Fine-tuning approaches using Qwen2.5-14B. Experimental results show that Prompt Engineering and Fine-tuning outperform the Baseline, with the fine-tuned small model slightly exceeding the baseline performance of GPT-OSS-120B, indicating that task-specific adaptation can offset model scale limitations.

발행기관:
한국멀티미디어학회
분류:
전자/정보통신공학

AI 법률 상담

이 논문의 주제에 대해 더 알고 싶으신가요?

460만+ 법률 자료에서 관련 판례·법령·해석례를 찾아 답변합니다

AI 상담 시작
소형 LLM을 활용한 강조표기 기반 특허 차이점 식별 | 멀티미디어학회논문지 2026 | AskLaw | 애스크로 AI