Problem
Research questions and friction points this paper is trying to address.
long-tailed concepts
fact-sensitivity
dense retrievers
scientific corpora
hallucination-prone LLM
REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement
🤖 AI Summary
针对科学文献检索中的长尾概念和高事实敏感性问题，提出REPAIR框架，通过迭代合成训练数据、诊断长尾概念及证据扩展等方法提升检索准确性。
📝 Abstract
Precise retrieval of scientific information is fundamentally constrained by long-tailed concepts and high fact-sensitivity of scientific corpora. These challenges often limit the effectiveness of dense retrievers and hallucination-prone LLM augmentation. To address this, we present REPAIR, a self-evolving data augmentation framework for scientific dense retrievers. REPAIR iteratively synthesizes training data to address knowledge gaps by cycling through diagnosis of long-tail concepts, API-guided evidence expansion, and differentiation via hard negative mining. This process effectively grounds retrieval in factual reality to resolve fine-grained distinctions. Extensive experiments demonstrate that REPAIR significantly outperforms 19 strong baselines on nine materials science and biomedical benchmarks. Our work highlights that diagnosing and factually augmenting data to long-tail deficits is essential for robust scientific retrieval.
Innovation
Methods, ideas, or system contributions that make the work stand out.
long-tail concepts
iterative refinement
fact-verified
data augmentation
dense retrievers
🔎 Similar Papers
No similar papers found.
