Salvato in:
Dettagli Bibliografici
Autori principali: Haas, Lukas, Yona, Gal, D'Antonio, Giovanni, Goldshtein, Sasha, Das, Dipanjan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.07968
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908876839845888
author Haas, Lukas
Yona, Gal
D'Antonio, Giovanni
Goldshtein, Sasha
Das, Dipanjan
author_facet Haas, Lukas
Yona, Gal
D'Antonio, Giovanni
Goldshtein, Sasha
Das, Dipanjan
contents We introduce SimpleQA Verified, a 1,000-prompt benchmark for evaluating Large Language Model (LLM) short-form factuality based on OpenAI's SimpleQA. It addresses critical limitations in OpenAI's benchmark, including noisy and incorrect labels, topical biases, and question redundancy. SimpleQA Verified was created through a rigorous multi-stage filtering process involving de-duplication, topic balancing, and source reconciliation to produce a more reliable and challenging evaluation set, alongside improvements in the autorater prompt. On this new benchmark, Gemini 2.5 Pro achieves a state-of-the-art F1-score of 55.6, outperforming other frontier models, including GPT-5. This work provides the research community with a higher-fidelity tool to track genuine progress in parametric model factuality and to mitigate hallucinations. The benchmark dataset, evaluation code, and leaderboard are available at: https://www.kaggle.com/benchmarks/deepmind/simpleqa-verified.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07968
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge
Haas, Lukas
Yona, Gal
D'Antonio, Giovanni
Goldshtein, Sasha
Das, Dipanjan
Computation and Language
We introduce SimpleQA Verified, a 1,000-prompt benchmark for evaluating Large Language Model (LLM) short-form factuality based on OpenAI's SimpleQA. It addresses critical limitations in OpenAI's benchmark, including noisy and incorrect labels, topical biases, and question redundancy. SimpleQA Verified was created through a rigorous multi-stage filtering process involving de-duplication, topic balancing, and source reconciliation to produce a more reliable and challenging evaluation set, alongside improvements in the autorater prompt. On this new benchmark, Gemini 2.5 Pro achieves a state-of-the-art F1-score of 55.6, outperforming other frontier models, including GPT-5. This work provides the research community with a higher-fidelity tool to track genuine progress in parametric model factuality and to mitigate hallucinations. The benchmark dataset, evaluation code, and leaderboard are available at: https://www.kaggle.com/benchmarks/deepmind/simpleqa-verified.
title SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge
topic Computation and Language
url https://arxiv.org/abs/2509.07968