- Study on medical data finds AI models can easily spread misinformation, even with minimal false input | Even 0.001% false data can disrupt the accuracy of large language models https://www.nature.com/articles/s41591-024-03445-1 7 comments science
Linked pages
- [2303.12712] Sparks of Artificial General Intelligence: Early experiments with GPT-4 https://arxiv.org/abs/2303.12712 911 comments
- [2401.11817] Hallucination is Inevitable: An Innate Limitation of Large Language Models https://arxiv.org/abs/2401.11817 493 comments
- Noun Project: Free Icons & Stock Photos for Everything https://thenounproject.com/ 296 comments
- [2005.14165] Language Models are Few-Shot Learners https://arxiv.org/abs/2005.14165 201 comments
- OpenAI API https://openai.com/api/ 158 comments
- [2303.13375] Capabilities of GPT-4 on Medical Challenge Problems https://arxiv.org/abs/2303.13375 135 comments
- [2302.10149] Poisoning Web-Scale Training Datasets is Practical https://arxiv.org/abs/2302.10149 95 comments
- [2101.00027] The Pile: An 800GB Dataset of Diverse Text for Language Modeling https://arxiv.org/abs/2101.00027 81 comments
- [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training https://arxiv.org/abs/2401.05566 18 comments
- [2210.07229] Mass-Editing Memory in a Transformer https://arxiv.org/abs/2210.07229 15 comments
- [2212.13894] LAMBADA: Backward Chaining for Automated Reasoning in Natural Language https://arxiv.org/abs/2212.13894 11 comments
- SlimPajama: A 627B token cleaned and deduplicated version of RedPajama - Cerebras https://www.cerebras.net/blog/slimpajama-a-627b-token-cleaned-and-deduplicated-version-of-redpajama 7 comments
- https://blog.allenai.org/dolma-3-trillion-tokens-open-llm-corpus-9a0ff4b8da64 5 comments
- NVIDIA to create AI ‘agents’ that outperform human nurses https://newatlas.com/technology/nvidia-hippocratic-ai-nurses/ 5 comments
- [2203.15556] Training Compute-Optimal Large Language Models https://arxiv.org/abs/2203.15556 0 comments
- [2009.03300] Measuring Massive Multitask Language Understanding https://arxiv.org/abs/2009.03300 0 comments
- Download | OpenWebTextCorpus https://skylion007.github.io/OpenWebTextCorpus/ 0 comments
- [2306.01116] The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only https://arxiv.org/abs/2306.01116 0 comments
- [2302.13971] LLaMA: Open and Efficient Foundation Language Models https://arxiv.org/abs/2302.13971 0 comments
- GitHub - Dao-AILab/flash-attention: Fast and memory-efficient exact attention https://github.com/Dao-AILab/flash-attention 0 comments
Related searches:
Search whole site: site:nature.com
Search title: Medical large language models are vulnerable to data-poisoning attacks | Nature Medicine
See how to search.