Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

GPT-4 Technical Report research paper by OpenAI, 2023

OpenAI · Foundation models · Mar 15, 2023 · 28,363 citations · 7 upvotes

Read on arXiv

What it shows

A multimodal model that passes a simulated bar exam with a score around the top 10% of test takers.

By OpenAI · arXiv 2303.08774 · PDF

Summarised by hand from the abstract.

More from OpenAI

All 8
ReasoningUnverifiedMar 5, 2026Reasoning Models Struggle to Control their Chains of ThoughtChain-of-thought controllability measures how effectively models can be constrained to follow reasoning steps, with findings showing significantly lower controllability in reasoning versus output generation, and varying impacts from model size, training methods, and task complexity.OpenAI37 citations41 upvotesRead →Alignment and safetySep 4, 2025Why Language Models HallucinateModels hallucinate because training and benchmarks reward confident guessing over saying they do not know.OpenAI391 citations200 upvotesRead →Alignment and safetyUnverifiedDec 21, 2024OpenAI o1 System CardThe o1 model series, trained with reinforcement learning and chain of thought, enhances safety and robustness by reasoning about policies, leading to superior performance on risk benchmarks while highlighting the need for robust alignment and risk management.OpenAI38 upvotesRead →Multimodal and roboticsUnverifiedOct 25, 2024GPT-4o System CardGPT-4o is an omnimodal autoregressive model trained to handle text, audio, image, and video inputs, offering high-performance outputs across these modalities, with particular strengths in vision and audio.OpenAI5,388 citations88 upvotesRead →Alignment and safetyMar 4, 2022Training language models to follow instructions with human feedbackInstructGPT: fine-tuning on human feedback made a 1.3B model preferred over the 175B GPT-3.OpenAI25.8k citations26 upvotesRead →Foundation modelsMay 28, 2020Language Models are Few-Shot LearnersGPT-3, a 175B-parameter model, does new tasks from a few examples in the prompt, with no fine-tuning.OpenAI66.4k citations21 upvotesRead →Training and scalingJan 23, 2020Scaling Laws for Neural Language ModelsLanguage model loss falls as a smooth power law as model size, data and compute grow.OpenAI9,592 citations12 upvotesRead →

Releases that name it

From releases.fru.dev
ReleaseApr 24, 2026Claude Opus 4.7, GPT-4 Turbo, GPT-4.1 Nano, and GPT-5.4 now available for Agentsretoolreleases.fru.dev →

Other foundation models papers

Topic
Foundation modelsOct 11, 2018BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingPre-training a Transformer to fill in masked words, then fine-tuning it, beat task-specific models across language understanding tests.Google125k citations33 upvotesRead →Foundation modelsFeb 27, 2023LLaMA: Open and Efficient Foundation Language ModelsOpen models from 7B to 65B trained only on public data; the 13B model beats GPT-3 on most benchmarks.Meta22.6k citations25 upvotesRead →Foundation modelsJul 31, 2024The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Meta20.8k citations119 upvotesRead →Foundation modelsUnverifiedMay 14, 2025Qwen3 Technical ReportQwen3, a unified series of large language models, integrates thinking and non-thinking modes, reduces computational resources, and achieves state-of-the-art performance across various tasks and languages.Alibaba (Qwen)10.1k citations339 upvotesRead →Foundation modelsMar 8, 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextRecalls details across millions of tokens of text, hours of video and days of audio.Google DeepMind4,190 citations65 upvotesRead →Foundation modelsUnverifiedNov 26, 2025Qwen3-VL Technical ReportQwen3-VL, a vision-language model, excels in text and multimodal understanding through advanced architectures and larger contexts, achieving superior performance across benchmarks.Alibaba (Qwen)3,178 citations164 upvotesRead →
About this paper
Citations
28,363, 3,397 influential · Semantic Scholar
Upvotes
7 · Hugging Face
Lab
OpenAI · on Companies · on Acquisitions · on Paydays · on Releases · on TechConf

Changes

CitationsNov 9, 2026Influential citations rose from 3,383 to 3,397.
CitationsNov 9, 2026Citations rose from 28,214 to 28,363.
CitationsNov 2, 2026Influential citations rose from 3,338 to 3,383.
CitationsNov 2, 2026Citations rose from 27,681 to 28,214.
CitationsOct 12, 2026Influential citations rose from 3,317 to 3,338.
CitationsOct 12, 2026Citations rose from 27,514 to 27,681.
CitationsOct 5, 2026Influential citations rose from 3,301 to 3,317.
CitationsOct 5, 2026Citations rose from 27,329 to 27,514.
CitationsSep 28, 2026Influential citations rose from 3,293 to 3,301.
CitationsSep 28, 2026Citations rose from 27,296 to 27,329.
CitationsSep 25, 2026Influential citations rose from 3,290 to 3,293.
CitationsSep 25, 2026Citations rose from 27,281 to 27,296.
New paperSep 24, 2026Added to the list.