Examples
Worked examples
- Is an instance
Using an LLM to draft a plain-language summary of a clinical paper, then human-reviewed for accuracy
Counter-examples
Looks similar, but isn't
- Not an instance
A human writing a one-paragraph summary based on their own reading is not AI summarisation
Editorial commentary
Abstractive AI summarisation is prone to hallucination — including content not in the source and omitting important caveats — so any AI-generated summary of a scholarly work should be human-verified. Where the summary is published, AI use is disclosable.
References
- Pasunuru et al. 2023 ‘Faithful Summarisation Survey’ TACL
- Maynez et al. 2020 ‘On Faithfulness and Factuality in Abstractive Summarisation’ ACL
Also known as
Automatic summarisation · LLM summarisation
Machine-readable encodings
Use in your systems
xml
<role vocab="credit"
vocab-identifier="https://casrai.org/dictionary/"
vocab-term="AI summarisation"
vocab-term-identifier="https://casrai.org/dictionary/term/ai-summarisation" />json
{
"@context": "https://schema.org",
"@type": "DefinedTerm",
"name": "AI summarisation",
"identifier": "https://casrai.org/dictionary/term/ai-summarisation",
"description": "The use of an AI system to produce a shorter version of a text that preserves its key information, including abstracts, lay summaries, executive summaries, and literature digests, whether extractive (sentence selection) or abstractive (paraphrasing).",
"inDefinedTermSet": "https://casrai.org/dictionary/domain/generative-ai-use-and-disclosure/",
"url": "https://casrai.org/dictionary/term/ai-summarisation",
"sameAs": [
"Automatic summarisation",
"LLM summarisation"
],
"license": "https://creativecommons.org/licenses/by/4.0/"
}
