ArticleRoyal Society open science2025
Generalization bias in large language model summarization of scientific research.
Article in Royal Society open science, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 31 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
31 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Artificial Intelligence for Evidence Synthesis of Emerging Biologics to Improve Skeletal Health in Osteogenesis Imperfecta: Systematic Review and Meta-Analysis.Journal of medical Internet research · 2026Pooled it
- Article
- Fostering cultural change in research through innovative knowledge sharing, evaluation, and community engagement strategies.NPJ science of learning · 2026Review
- Article
- Illusions of Understanding from Outsourcing Thinking to LLMs.Computational brain & behavior · 2026Article
- From Cluster to Claim: Calibrating Interpretation in Single-Cell Transcriptomics.Advanced genetics (Hoboken, N.J.) · 2026Article
- Quantifying the prevalence and impact of overreaching causal claims in social science.Nature human behaviour · 2026Article
- When machines misread science: creating guardrails for human and AI interpretation of biomedical research.NPJ digital medicine · 2026Article
- Generics in science communication: Misaligned interpretations across laypeople, scientists, and large language models.Public understanding of science (Bristol, England) · 2026Article
- Psychedelics, the media portrayal and large-language model evaluations.BJPsych open · 2026Article
- A brief review of some artificial intelligence methods in nephrology.Pediatric nephrology (Berlin, Germany) · 2026Review
- Plain Language Summarization of Environmental Health Research Using Generative AI: Community-Engaged Qualitative Study.Journal of medical Internet research · 2026Article
- Accuracy, quality, and readability analyses of responses from large language models to questions on pediatric dental sedation.BMC oral health · 2026Article
- Using Large Language Models to Summarize Evidence in Biomedical Articles: Exploratory Comparison Between AI- and Human-Annotated Bibliographies.JMIR formative research · 2026Article
- Why can't epidemiology be automated (yet)?International journal of epidemiology · 2026Article
- Scientific autonomy in the structural bubble: from institutional bias to AI-mediated consensus.Frontiers in research metrics and analytics · 2026Article
- Clinical warrant in medical LLM evaluation.Frontiers in digital health · 2026Review
- DiscoVerse: multi-agent pharmaceutical co-scientist for traceable drug discovery and reverse translation.Frontiers in artificial intelligence · 2026Article
- Assessment of artificial intelligence chatbots in responding to dental occlusion questions: a comparative study.BMC oral health · 2025Article
- Decoding Alexander the Great's gastrointestinal cause of death using artificial wisdom: An artificial intelligence-human inquiry into a medical mystery.World journal of gastroenterology · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Artificial intelligence chatbots driven by large language models (LLMs) have the potential to increase public science literacy and support scientific research, as they can quickly summarize complex scientific information in accessible terms. However, when summarizing scientific texts, LLMs may omit details that limit the scope of research conclusions, leading to generalizations of results broader than warranted by the original study. We tested 10 prominent LLMs, including ChatGPT-4o, ChatGPT-4.5, DeepSeek, LLaMA 3.3 70B, and Claude 3.7 Sonnet, comparing 4900 LLM-generated summaries to their original scientific texts. Even when explicitly prompted for accuracy, most LLMs produced broader generalizations of scientific results than those in the original texts, with DeepSeek, ChatGPT-4o, and LLaMA 3.3 70B overgeneralizing in 26-73% of cases. In a direct comparison of LLM-generated and human-authored science summaries, LLM summaries were nearly five times more likely to contain broad generalizations (odds ratio = 4.85, 95% CI [3.06, 7.70],
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.