LOCA: Logical Chain Augmentation for Scientific Corpus Cleaning

ICLR 2026 Conference Submission14769 Authors

Keywords: scientific corpus cleaning, logical chain, AI for science, LLMs

Abstract: While Large Language Models (LLMs) excel in general domains, their reliability often falls short in scientific problem-solving. The advancement of scientific AI depends on large-scale, high-quality corpora. However, existing scientific question-answering (QA) datasets suffer from high error rates, frequently resulting from logical leaps and implicit reasoning within the answers. To address this issue, we introduce LOCA (Logical Chain Augmentation), a novel framework for automatically cleaning scientific corpora, implemented through an augment-and-review loop. At its core, LOCA enhances raw answers by completing missing logical steps and explicitly separating the underlying scientific principle from its subsequent derivation. By applying LOCA to challenging scientific corpora, we demonstrate that it can automatically filter noisy datasets, typically reducing the error rate from as high as 20\% to below 2\%. LOCA provides a scalable and effective methodology for creating high-quality scientific corpora, paving the way for more reliable training and evaluation of scientific AI.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 14769