Large Language Models
Pretraining and foundation/decoder LLMs and model families (GPT, LLaMA, PaLM, Mistral, …).
A topic in the Science corpus, drawn from 1,003 papers.
Trusted voices in Large Language Models
Ordered by the trust Large Language Models's own network concentrates on each researcher, most first.
- Jacob Devlin — trusted by 1,913 researchers here
- Ming-Wei Chang — trusted by 1,893 researchers here
- Kristina Toutanova — trusted by 1,891 researchers here
- Kenton C. T. Lee — trusted by 1,891 researchers here
- Alec Radford — trusted by 1,584 researchers here
- Karthik Narasimhan — trusted by 946 researchers here
- Yoshua Bengio — trusted by 643 researchers here
- Kenneth Heafield — trusted by 362 researchers here
- Quoc V. Le — trusted by 476 researchers here
- Jeff Wu — trusted by 456 researchers here
- Noam Shazeer — trusted by 425 researchers here
- Dario Amodei — trusted by 414 researchers here
Most-cited papers in Large Language Models
Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2019, North American Chapter of the Association for Computational Linguistics) — 118,136 citations
- Deep Learning (2016) — 78,707 citations
- Language Models are Few-Shot Learners (2020, Neural Information Processing Systems) — 61,005 citations
- RoBERTa: A Robustly Optimized BERT Pretraining Approach (2019, arXiv.org) — 30,530 citations
- Language Models are Unsupervised Multitask Learners (2019) — 29,506 citations
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2019, Journal of machine learning research) — 26,606 citations
- GPT-4 Technical Report (2023) — 26,133 citations
- Training language models to follow instructions with human feedback (2022, Neural Information Processing Systems) — 22,660 citations
- LLaMA: Open and Efficient Foundation Language Models (2023, arXiv.org) — 20,887 citations
- Chain of Thought Prompting Elicits Reasoning in Large Language Models (2022, Neural Information Processing Systems) — 20,310 citations
- Llama 2: Open Foundation and Fine-Tuned Chat Models (2023, arXiv.org) — 17,670 citations
- The Llama 3 Herd of Models (2024) — 17,085 citations
- Improving Language Understanding by Generative Pre-Training (2018) — 15,103 citations
- 5分で分かる!? 有名論文ナナメ読み:Jacob Devlin et al. : BERT : Pre-training of Deep Bidirectional Transformers for Language Understanding (2020) — 14,205 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension (2019) — 13,006 citations
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model (2023, Neural Information Processing Systems) — 9,702 citations
- XLNet: Generalized Autoregressive Pretraining for Language Understanding (2019, Neural Information Processing Systems) — 9,461 citations
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models (2023) — 8,665 citations
- Scaling Laws for Neural Language Models (2020, arXiv.org) — 8,567 citations
- Machine learning: Trends, perspectives, and prospects (2015) — 8,448 citations
- PaLM: Scaling Language Modeling with Pathways (2022, Journal of machine learning research) — 8,214 citations
- On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜 (2021) — 7,969 citations
- A Neural Probabilistic Language Model (2003) — 7,861 citations
- Robust Speech Recognition via Large-Scale Weak Supervision (2022, International Conference on Machine Learning) — 7,824 citations
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models (2024) — 7,648 citations
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining (2019) — 7,641 citations
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (2019) — 7,601 citations
- Large Language Models are Zero-Shot Reasoners (2022) — 7,591 citations
- Efficient Memory Management for Large Language Model Serving with PagedAttention (2023) — 7,142 citations
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (2022) — 7,032 citations
- On the Opportunities and Risks of Foundation Models (2021) — 6,923 citations
- Flamingo: a Visual Language Model for Few-Shot Learning (2022, Neural Information Processing Systems) — 6,220 citations
- Recurrent neural network based language model (2010) — 6,125 citations
- The Power of Scale for Parameter-Efficient Prompt Tuning (2021) — 5,785 citations
- Longformer: The Long-Document Transformer (2020) — 5,720 citations
- Improved Baselines with Visual Instruction Tuning (2023) — 5,499 citations
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning (2025, Nature) — 5,477 citations
- Finetuned Language Models Are Zero-Shot Learners (2021) — 5,221 citations
- Evolutionary-scale prediction of atomic level protein structure with a language model (2022) — 5,058 citations
- OPT: Open Pre-trained Transformer Language Models (2022) — 4,844 citations
- Toolformer: Language Models Can Teach Themselves to Use Tools (2023, Neural Information Processing Systems) — 4,753 citations
- A Survey of Large Language Models (2023) — 4,706 citations
- Large language models encode clinical knowledge (2022) — 4,703 citations
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks (2019) — 4,585 citations
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models (2023) — 4,499 citations
- Transformer-XL: Attentive Language Models beyond a Fixed-Length Context (2019) — 4,418 citations
- Lost in the Middle: How Language Models Use Long Contexts (2023) — 4,355 citations
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (2021, Journal of machine learning research) — 4,336 citations
- Sparks of Artificial General Intelligence: Early experiments with GPT-4 (2023) — 4,318 citations
- Scaling Instruction-Finetuned Language Models (2022, Journal of machine learning research) — 4,301 citations
Most active researchers
By papers in this topic: a volume measure, not trust.
- Luke S. Zettlemoyer — 23 papers
- Percy Liang — 18 papers
- Jianfeng Gao — 16 papers
- Furu Wei — 16 papers
- Denny Zhou — 15 papers
- Jason Wei — 13 papers
- Colin Raffel — 13 papers
- Quoc V. Le — 13 papers
- Michael Lewis — 13 papers
- Stella Biderman — 12 papers
- Noah A. Smith — 12 papers
- Hinrich Schütze — 12 papers