Article

WITHDRAWN: From Interpolation to Extrapolation: How Language Models Theorize in Data-Sparse Regimes

2026-02-17

Abstract excerpt

<title>Abstract</title> <p> When large language models (LLMs) generate citations in sparse domains, they frequently produce non-existent but theoretically coherent references. We argue these are not random errors but instances of <bold>abductive extrapolation</bold> : extending learned structures to infer what research <italic>should</italic> exist. Using a 2×2×2 factorial design (N = 192 citations), we mani...

Topics

Open a Topic to create a Post that cites this publication.

Genomics and Rare Diseases

Identifiers and source

Literature Corpus work: bd6d557f-6184-5a16-b920-56c54f31b123
DOI: 10.21203/rs.3.rs-8875396/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

WITHDRAWN: From Interpolation to Extrapolation: How Language Models Theorize in Data-Sparse RegimesDOI 10.21203/rs.3.rs-8875396/v1Read

Analysis: LLM hallucinations in the wild: Large-scale evidence from non-existent citationsSemantic proximity Read

Model shopping: how answer selection across AI models inflates scientific error ratesSemantic proximity Read

Classifying 25 Misinterpretations of Statistical Tests: A Comparison of Six Large Language ModelsSemantic proximity Read

fAIr science — How AI can support a transparent biopsychological research cycleSemantic proximity Read

fAIr science — How AI can support a transparent biopsychological research cycleSemantic proximity Read

Redistributing Epistemic Labor: Prior Knowledge Shapes How Effectively Students Use Large Language ModelsSemantic proximity Read

Initial indications of generative AI influence in linguistics research abstracts: Evidence from a large-scale lexical frequency analysis between 2018 and 2025Semantic proximity Read

A Multi-Factor Evaluation of Fidelity in LLM-Based Cross-Cultural SurrogatesSemantic proximity Read

Harnessing GPT for Enhanced Academic Writing: Evidence from a Field Experiment with Early-Career Researchers in the Social SciencesSemantic proximity Read

Mind the Gap: From Plausible to Valid Self-Explanations in Large Language ModelsSemantic proximity Read

Impersonal Statements: LLM-Era College Admissions Essays Exhibit Deep Homogenization Despite Lexical DiversitySemantic proximity Read

Large language model research: Knowledge structure, thematic evolution, and future research agendaSemantic proximity Read