Summarization
DescriptionEvaluates an LLM's ability to accurately summarize long texts from diverse sources such as YouTube video transcripts, websites, PDFs, and direct text inputs. It also assesses the model's capacity to follow detailed user instructions to extract specific data insights. The dataset consists of 41 unique entries in English, which have been translated into Afrikaans, Brazilian Portuguese, and Polish using machine translation.Number of Samples164LanguageEnglish, Afrikaans, Brazilian Portuguese, PolishProviderToqanEvaluation MethodAuto-evaluation with GPT4-Turbo over ground-truth summaries.Data Collection PeriodFebruary 2022 - October 2023
Language
Language of the source document
Complexity
The complexity level of the summary requests.
Last updated: November 12, 2024
Share this view
# | Model | Provider | Size | Chunk Size | Adherence To Instructions | Accuracy of Content | Quality of Writing |
---|---|---|---|---|---|---|---|
No results. |