Salvato in:
Dettagli Bibliografici
Autori principali: Soós, Dominik, Jiang, Meng, Wu, Jian
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.31099
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916064987709440
author Soós, Dominik
Jiang, Meng
Wu, Jian
author_facet Soós, Dominik
Jiang, Meng
Wu, Jian
contents Science news is an important medium to communicate discoveries between the research communities and the public. Yet, most metrics for generated or summarized text evaluate semantic similarity and factual consistency, but do not measure how much knowledge readers learn from the news. We introduce KnowledgeGain, a metric that evaluates the quality of science news by measuring how much knowledge readers gained after reading it. To evaluate the metric, we first performed a controlled human study and showed that the metric successfully captures the differential knowledge gained by human readers reading different types of science media. The data allowed us to calibrate a prompt-only LLM reader simulator. We use it to rank and filter candidate articles before human evaluation. A second human study shows that articles selected with this simulator improve post-reading accuracy and normalized KnowledgeGain over a strong generation baseline. Our work is a step toward generating science news that better meets the knowledge and comprehension goals of Bloom's Taxonomy.
format Preprint
id arxiv_https___arxiv_org_abs_2605_31099
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learning
Soós, Dominik
Jiang, Meng
Wu, Jian
Computation and Language
Artificial Intelligence
Science news is an important medium to communicate discoveries between the research communities and the public. Yet, most metrics for generated or summarized text evaluate semantic similarity and factual consistency, but do not measure how much knowledge readers learn from the news. We introduce KnowledgeGain, a metric that evaluates the quality of science news by measuring how much knowledge readers gained after reading it. To evaluate the metric, we first performed a controlled human study and showed that the metric successfully captures the differential knowledge gained by human readers reading different types of science media. The data allowed us to calibrate a prompt-only LLM reader simulator. We use it to rank and filter candidate articles before human evaluation. A second human study shows that articles selected with this simulator improve post-reading accuracy and normalized KnowledgeGain over a strong generation baseline. Our work is a step toward generating science news that better meets the knowledge and comprehension goals of Bloom's Taxonomy.
title KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.31099