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