Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection
Reducing hallucinations in Large Language Models (LLMs) is essential for improving the accuracy of data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual documents but fail to consider relationships across a corpus. This paper introduces Peer Context Outlier Detection (P-COD), a novel approach that uses the relationships between documents to improve extraction accuracy. Our application domain is in scientific literature summarization, where papers with similar experiment settings should draw similar conclusions. By comparing extracted data to validated peer information within the corpus, we adjust confidence scores and flag low-confidence results for expert review. High-confidence results, supported by peer validation, are considered reliable. Our experiments demonstrate up to 98% precision in outlier detection across 6 domains of science, demonstrating that our design reduces hallucinations, enhances trust in automated systems, and allows researchers to focus on ambiguous cases, streamlining the data extraction workflows.
Code (0)
등록된 구현이 없습니다.
Tasks
Prompt EngineeringOutlier DetectionSimilar Papers 제목 키워드 기반
Compound Deception in Elite Peer Review: A Failure Mode Taxonomy of 100 Fabricated Citations at NeurIPS 2025
Large language models (LLMs) are increasingly used in academic writing workflows, yet they frequently hallucinate by generating citations to sources that do not exist. This study analyzes 100 AI-generated hallucinated ci…
Decontamination of the scientific literature
Research misconduct and frauds pollute the scientific literature. Honest errors and malevolent data fabrication, image manipulation, journal hijacking, and plagiarism passed peer review unnoticed. Problematic papers dece…
Image ManipulationMeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning
The accurate extraction of scientific measurements from literature is a critical yet challenging task in AI4Science, enabling large-scale analysis and integration of quantitative research findings. However, Large Languag…
PaperQA: Retrieval-Augmented Generative Agent for Scientific Research
Large Language Models (LLMs) generalize well across language tasks, but suffer from hallucinations and uninterpretability, making it difficult to assess their accuracy without ground-truth. Retrieval-Augmented Generation…
ArticlesInformation RetrievalQuestion AnsweringRAG+2An Audit on the Perspectives and Challenges of Hallucinations in NLP
We audit how hallucination in large language models (LLMs) is characterized in peer-reviewed literature, using a critical examination of 103 publications across NLP research. Through the examination of the literature, we…
HallucinationSurvey