Errors of LLM-Assisted Literature Retrieval in Environmental Science: A Comparison Study of Abstract versus Full-text Based Prompts
Abstract
Large language models (LLMs) are increasingly used for literature search and synthesis. However, it is unclear whether they retrieve accurate bibliographic information in environmental science. Therefore, we quantitatively compared the errors of widely used LLM platforms in retrieving references related to original articles from five leading environmental science journals (Energy and Environmental Science, Nature Sustainability, Nature Climate Change, Lancet Planetary Health, and Environmental Science and Technology) published in 2024 to 2025. Claude, ChatGPT, Grok, DeepSeek, Perplexity, and Gemini were used as the LLM platforms. LLMs retrieved 10 references for each of the 50 randomly selected original article using either the article's abstract or its full-text as prompt. The retrieved references were subject to a multimetric score ratio combining validity of bibliographic data, Google Scholar link, digital object identifier, Scopus Electronic Identifier and relevance score (cited by or being the index paper), and the proportion of complete fabrication that failed all metrics. Abstract-only prompt yielded significantly higher accuracy than full-text one. This advantage was confirmed in multilevel mixed-effect multivariable regression after adjusting for journal, platform, and output order. Source journal and the position of a reference within the output list were also independently associated with retrieval accuracy, with lower-listed references associated with lower accuracy. These findings suggest that LLM assisted literature retrieval in environmental science remains moderately accurate and overall inconsistent, varying significantly by platform, journal, prompt type, and output position. Abstract-based prompting, as task-aligned information compression, may outperform full-text one in literature retrieval. Caution should be used when generalizing our findings.
Related
- Comment on Vogels et al.'s (2024) "Bayesian Structure Learning in Undirected Gaussian Graphical Models: Literature Review with Empirical Comparison": An updated performance check using BGGM
- Transmissive RIS-Assisted Vehicular Direct-to-Satellite Communications: Opportunities, Limitations, and Comparison with Phased Arrays
- Perceived factors associated with self-reported AI-assisted academic cheating among undergraduate students: Evidence from ethical ambiguity, technological affordances, institutional gaps, academic pressure, and peer comparison
- On abstract commensurators of groups
- textsc{Athanor}: local search over abstract constraint specifications
BibTeX
@misc{chen2026errors,
title = {{Errors of LLM-Assisted Literature Retrieval in Environmental Science: A Comparison Study of Abstract versus Full-text Based Prompts}},
author = {Yanjun Chen and Yongfeng Zhang and Lanjing Zhang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.05690},
eprint = {2610.05690},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.05690},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Errors of LLM-Assisted Literature Retrieval in Environmental Science: A Comparison Study of Abstract versus Full-text Based Prompts
AU - Yanjun Chen
AU - Yongfeng Zhang
AU - Lanjing Zhang
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2610.05690
UR - https://arxiv.org/abs/2610.05690
AB - Large language models (LLMs) are increasingly used for literature search and synthesis. However, it is unclear whether they retrieve accurate bibliographic information in environmental science. Therefore, we quantitatively compared the errors of widely used LLM platforms in retrieving references related to original articles from five leading environmental science journals (Energy and Environmental Science, Nature Sustainability, Nature Climate Change, Lancet Planetary Health, and Environmental Science and Technology) published in 2024 to 2025. Claude, ChatGPT, Grok, DeepSeek, Perplexity, and Gemini were used as the LLM platforms. LLMs retrieved 10 references for each of the 50 randomly selected original article using either the article's abstract or its full-text as prompt. The retrieved references were subject to a multimetric score ratio combining validity of bibliographic data, Google Scholar link, digital object identifier, Scopus Electronic Identifier and relevance score (cited by or being the index paper), and the proportion of complete fabrication that failed all metrics. Abstract-only prompt yielded significantly higher accuracy than full-text one. This advantage was confirmed in multilevel mixed-effect multivariable regression after adjusting for journal, platform, and output order. Source journal and the position of a reference within the output list were also independently associated with retrieval accuracy, with lower-listed references associated with lower accuracy. These findings suggest that LLM assisted literature retrieval in environmental science remains moderately accurate and overall inconsistent, varying significantly by platform, journal, prompt type, and output position. Abstract-based prompting, as task-aligned information compression, may outperform full-text one in literature retrieval. Caution should be used when generalizing our findings.
ER -