Gemini: A Family of Highly Capable Multimodal Models
Technical report by the Gemini Team at Google, arXiv version 1 of 19 December 2023. Recorded as a document so that the works its text cites can be recorded; evidence is scoped to the inspected version 1.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- No authorship claim recorded yet. The source record lists Gemini Team, Google.
- Dates
- No date claim recorded yet. The source record gives the publication date as 2023-12-19.
- Exact source
- Gemini: A Family of Highly Capable Multimodal Models Gemini Team, Google · published 2023-12-19 · Pinned arXiv 2312.11805v1, submitted 19 December 2023; section 3 inspected directly. The mutable DeepMind PDF is a later revision and is not the historical evidence.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Cites · 25
Explicit references in this document. Citation is neither agreement nor influence.
- Attention Is All You NeedGemini: A Family of Highly Capable Multimodal Models cites Attention Is All You Need.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Attention Is All You Need: document page →
- BoolQ: Exploring the Surprising Difficulty of Natural Yes/No QuestionsGemini: A Family of Highly Capable Multimodal Models cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions: document page →
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsGemini: A Family of Highly Capable Multimodal Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Chain-of-Thought Prompting Elicits Reasoning in Large Language Models: document page →
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve ThemGemini: A Family of Highly Capable Multimodal Models cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them: document page →
- Training Compute-Optimal Large Language ModelsGemini: A Family of Highly Capable Multimodal Models cites Training Compute-Optimal Large Language Models.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Training Compute-Optimal Large Language Models: document page →
- Constitutional AI: Harmlessness from AI FeedbackGemini: A Family of Highly Capable Multimodal Models cites Constitutional AI: Harmlessness from AI Feedback.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Constitutional AI: Harmlessness from AI Feedback: document page →
- Ethical and social risks of harm from Language ModelsGemini: A Family of Highly Capable Multimodal Models cites Ethical and social risks of harm from Language Models.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Ethical and social risks of harm from Language Models: document page →
- Evaluating Large Language Models Trained on CodeGemini: A Family of Highly Capable Multimodal Models cites Evaluating Large Language Models Trained on Code.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Evaluating Large Language Models Trained on Code: document page →
- GPT-4 Technical ReportGemini: A Family of Highly Capable Multimodal Models cites GPT-4 Technical Report.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗GPT-4 Technical Report: document page →
- HellaSwag: Can a Machine Really Finish Your Sentence?Gemini: A Family of Highly Capable Multimodal Models cites HellaSwag: Can a Machine Really Finish Your Sentence?.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗HellaSwag: Can a Machine Really Finish Your Sentence?: document page →
- Training language models to follow instructions with human feedbackGemini: A Family of Highly Capable Multimodal Models cites Training language models to follow instructions with human feedback.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Training language models to follow instructions with human feedback: document page →
- Language Models are Few-Shot LearnersGemini: A Family of Highly Capable Multimodal Models cites Language Models are Few-Shot Learners.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Language Models are Few-Shot Learners: document page →
- Language Models are Unsupervised Multitask LearnersGemini: A Family of Highly Capable Multimodal Models cites Language Models are Unsupervised Multitask Learners.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Language Models are Unsupervised Multitask Learners: document page →
- Llama 2: Open Foundation and Fine-Tuned Chat ModelsGemini: A Family of Highly Capable Multimodal Models cites Llama 2: Open Foundation and Fine-Tuned Chat Models.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Llama 2: Open Foundation and Fine-Tuned Chat Models: document page →
- LLaMA (2023 paper)Gemini: A Family of Highly Capable Multimodal Models cites LLaMA: Open and Efficient Foundation Language Models.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗LLaMA (2023 paper): document page →
- MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual ContextsGemini: A Family of Highly Capable Multimodal Models cites MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts: document page →
- Measuring Massive Multitask Language UnderstandingGemini: A Family of Highly Capable Multimodal Models cites Measuring Massive Multitask Language Understanding.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Measuring Massive Multitask Language Understanding: document page →
- Measuring Mathematical Problem Solving With the MATH DatasetGemini: A Family of Highly Capable Multimodal Models cites Measuring Mathematical Problem Solving With the MATH Dataset.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Measuring Mathematical Problem Solving With the MATH Dataset: document page →
- Natural Questions: A Benchmark for Question Answering ResearchGemini: A Family of Highly Capable Multimodal Models cites Natural Questions: A Benchmark for Question Answering Research.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Natural Questions: A Benchmark for Question Answering Research: document page →
- PaLM: Scaling Language Modeling with PathwaysGemini: A Family of Highly Capable Multimodal Models cites PaLM: Scaling Language Modeling with Pathways.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗PaLM: Scaling Language Modeling with Pathways: document page →
- Scaling Language Models: Methods, Analysis & Insights from Training GopherGemini: A Family of Highly Capable Multimodal Models cites Scaling Language Models: Methods, Analysis & Insights from Training Gopher.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Scaling Language Models: Methods, Analysis & Insights from Training Gopher: document page →
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsGemini: A Family of Highly Capable Multimodal Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Self-Consistency Improves Chain of Thought Reasoning in Language Models: document page →
- Sequence to Sequence Learning with Neural NetworksGemini: A Family of Highly Capable Multimodal Models cites Sequence to Sequence Learning with Neural Networks.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Sequence to Sequence Learning with Neural Networks: document page →
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human FeedbackGemini: A Family of Highly Capable Multimodal Models cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback: document page →
- Training Verifiers to Solve Math Word ProblemsGemini: A Family of Highly Capable Multimodal Models cites Training Verifiers to Solve Math Word Problems.2023-12-19 · publication · Stated in source · Supported Inspect claim & evidence ↗Training Verifiers to Solve Math Word Problems: document page →
Not recorded for this document: cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.