paper-with-me

홈 › Papers

Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering

2025-08-21 · Bolei He, Xinran He, Run Shao, Shanfu Shu, Xianwei Xue, Mingquan Cheng, Haifeng Li, Zhenhua Ling arxiv

Large Language Models (LLMs) perform well in general QA but often struggle in domain-specific scenarios. Retrieval-Augmented Generation (RAG) introduces external knowledge but suffers from hallucinations and latency due to noisy retrievals. Continued pretraining internalizes domain knowledge but is costly and lacks cross-domain flexibility. We attribute this challenge to the long-tail distribution of domain knowledge, which leaves partial yet useful internal knowledge underutilized. We further argue that knowledge acquisition should be progressive, mirroring human learning: first understanding concepts, then applying them to complex reasoning. To address this, we propose Selct2Know (S2K), a cost-effective framework that internalizes domain knowledge through an internal-external knowledge self-selection strategy and selective supervised fine-tuning. We also introduce a structured reasoning data generation pipeline and integrate GRPO to enhance reasoning ability. Experiments on medical, legal, and financial QA benchmarks show that S2K consistently outperforms existing methods and matches domain-pretrained LLMs with significantly lower cost.

📄 PDF Abstract BibTeX arXiv:2508.15213

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection

2025-02-10 · Yan Weng, Fengbin Zhu, Tong Ye, Haoyan Liu 외

Retrieval-Augmented Generation (RAG), which integrates external knowledge into Large Language Models (LLMs), has proven effective in enabling LLMs to produce more accurate and reliable responses. However, it remains a si…

Natural QuestionsRAGRetrievalRetrieval-augmented Generation

Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions

2024-02-21 · Hongru Wang, Boyang Xue, Baohang Zhou, Tianhua Zhang 외

Previous research has typically concentrated on leveraging the internal knowledge of Large Language Models (LLMs) to answer known questions (i.e., \textit{internal reasoning such as generate-then-read}). In contrast, for…

Binary ClassificationOpen-Domain Question AnsweringQuestion AnsweringRetrieval

KnowRL: Teaching Language Models to Know What They Know

2025-10-13 · Sahil Kale, Devendra Singh Dhami arxiv

Truly reliable AI requires more than simply scaling up knowledge; it demands the ability to know what it knows and when it does not. Yet recent research shows that even the best LLMs misjudge their own competence in more…

Reinforcement Learning

Internal and External Knowledge Interactive Refinement Framework for Knowledge-Intensive Question Answering

2024-08-23 · Haowei Du, Dongyan Zhao

Recent works have attempted to integrate external knowledge into LLMs to address the limitations and potential factual errors in LLM-generated content. However, how to retrieve the correct knowledge from the large amount…

HallucinationQuestion AnsweringRetrieval

Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant Knowledge

2025-11-01 · Qi Luo, Xiaonan Li, Junqi Dai, Shuang Cheng 외 arxiv

Retrieval-Augmented Generation has shown remarkable results to address Large Language Models' hallucinations, which usually uses a large external corpus to supplement knowledge to LLMs. However, with the development of L…