Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection

• URL: http://arxiv.org/abs/2604.01461v1
• Date: Wed, 01 Apr 2026 23:15:59 GMT
• Title: Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection
• Abstract summary: This paper introduces Peer Context Outlier Detection (P-COD), a novel approach that uses the relationships between documents to improve extraction accuracy.<n>By comparing extracted data to validated peer information within the corpus, we adjust confidence scores and flag low-confidence results for expert review.<n>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.
• Score: 15.38900394412587
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Detection and Interpretability Analysis of Quotation Errors by Large Language Models [3.806421007129287]
  This paper proposes the task of 'automated detection of quotation errors'<n>The fine-tuning approach for large language models (LLMs) is applied to the task of automated detection of quotation errors.<n> interpretability analysis is conducted on the model's output results.
  arXiv  Detail & Related papers  (2026-06-07T12:01:48Z)
• Combining Trained Models in Reinforcement Learning [0.0]
  Deep reinforcement learning (DRL) has delivered strong results in domains such as Atari and Go, but it still suffers from high sample cost and weak transfer beyond the training setting.<n>A common response is to reuse information from previously trained models through transfer, distillation, ensemble methods, or federated training.<n>This paper presents a PRISMA-guided systematic review of empirical studies on pretrained knowledge reuse in DRL.
  arXiv  Detail & Related papers  (2026-05-04T02:37:55Z)
• Can Large Language Models Detect Methodological Flaws? Evidence from Gesture Recognition for UAV-Based Rescue Operation Based on Deep Learning [0.0]
  We analyze a gesture-recognition paper reporting near-perfect accuracy on a small, human-centered dataset.<n>We first show that the evaluation protocol is consistent with subject-level data leakage due to non-independent training and test splits.<n>We then assess whether this flaw can be detected independently by six state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2026-03-23T11:39:16Z)
• Context Selection for Hypothesis and Statistical Evidence Extraction from Full-Text Scientific Articles [7.537972017257894]
  We study a sequential full-text extraction setting, where the statement of a primary finding in an article's abstract is linked to a corresponding hypothesis statement in the paper body.<n>We find that targeted context selection consistently improves hypothesis extraction relative to full-text prompting.<n>Even with oracle paragraphs, performance remains moderate, indicating persistent extractor limitations in handling hybrid numeric-textual statements.
  arXiv  Detail & Related papers  (2026-03-22T12:28:21Z)
• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era [51.63024682584688]
  Large language models (LLMs) introduce a new risk: fabricated references that appear plausible but correspond to no real publications.<n>We present the first comprehensive benchmark and detection framework for hallucinated citations in scientific writing.<n>Our framework significantly outperforms prior methods in both accuracy and interpretability.
  arXiv  Detail & Related papers  (2026-02-26T19:17:39Z)
• PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review [54.141490756509306]
  We introduce PaperAudit-Bench, which consists of two components: PaperAudit-Dataset, an error dataset, and PaperAudit-Review, an automated review framework.<n>Experiments on PaperAudit-Bench reveal large variability in error detectability across models and detection depths.<n>We show that the dataset supports training lightweight LLM detectors via SFT and RL, enabling effective error detection at reduced computational cost.
  arXiv  Detail & Related papers  (2026-01-07T04:26:12Z)
• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• Improved Evidence Extraction for Document Inconsistency Detection with LLMs [10.610567456326235]
  We introduce new comprehensive evidence-extraction metrics and a redact-and-retry framework with constrained filtering.<n>We back our claims with promising experimental results.
  arXiv  Detail & Related papers  (2026-01-06T00:58:20Z)
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection [71.59834293521074]
  We develop a framework to distinguish between human-authored and machine-generated text.<n>Our method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset.<n>Code, pretrained weights, and demo will be released.
  arXiv  Detail & Related papers  (2025-10-07T08:14:45Z)
• Making Document-Level Information Extraction Right for the Right Reasons [19.00249049142611]
  Document-level information extraction is a flexible framework compatible with applications where information is not necessarily localized in a single sentence. This work studies how to ensure that document-level neural models make correct inferences from complex text and make those inferences in an auditable way.
  arXiv  Detail & Related papers  (2021-10-14T19:52:47Z)
• SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction [51.27558374091491]
  We propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for relation extraction. Based on a broad spectrum of carefully designed tasks, our proposed SAIS method not only extracts relations of better quality due to more effective supervision, but also retrieves the corresponding supporting evidence more accurately.
  arXiv  Detail & Related papers  (2021-09-24T17:37:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.