Hyung Won Chung, Le Hou, Shayne Longpre
Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, Dasha Valter, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, Jason Wei
2022 · arXiv
Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1) scaling the number of tasks, (2) scaling the model size, and (3) finetuning on chain-of-thought data. We find that instruction finetuning with the above aspects dramatically improves performance on a variety of model classes (PaLM, T5, U-PaLM), prompting setups (zero-shot, few-shot, CoT), and evaluation benchmarks (MMLU, BBH, TyDiQA, MGSM, open-ended generation). For instance, Flan-PaLM 540B instruction-finetuned on 1.8K tasks outperforms PALM 540B by a large margin (+9.4% on average). Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints, which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.
Metadata: arXiv. Abstracts retain their original authors’ rights.
Original HN comments, with labels from simple text rules. A label describes the whole comment and may miss context or irony. Read the discussion to make up your own mind. About the labels
4 selected excerpts · 4 total mentions
>OpenAI hasn’t told us why ChatGPT is so much better than other models Here's the thing.... It's not. Unless you restrict the pool to models you know about. https://crfm.stanford.edu/helm/latest/?group=core_scenarios And Again, chatGPT was not the general SOTA LLM. https://arxiv.org/abs/2210.11416 So in the research world with detailed papers explaining what and what not, we had models that were better.
11B parameters, so I guess it's FLAN-T5[1]? combined with retrieval transformer (something like RETRO[2])? 1. https://arxiv.org/abs/2210.11416 2. https://arxiv.org/abs/2112.04426
BLOOM[0] is another 176B multilingual open-source model whose weights were published. However, running it locally requires 8 A6000 GPUs. The GPU cost alone is roughly $37K. Also, there is the concern of performance. The Chinchilla[1] paper indicates that most model sizes trained so far received too little token training (or were too big) to reach an optimal performance per energy expenditure. Furthermore, the InstructGPT[2] and more recently Flan[3] papers show that various finetuning techniques achieve significant gains, without which the result is a bit meh. The dark secret of GPT-3 is that the model available on the OpenAI website is heavily fine-tuned, even compared to the InstructGPT paper. [0]: https://huggingface.co/bigscience/bloom [1]: https://arxiv.org/abs/2203.15556 [2]: https://arxiv.org/abs/2203.02155 [3]: https://arxiv.org/pdf/2210.11416.pdf
GPT 3.5 is definitely not comparable to Palm. You can see some benchmarks here. https://crfm.stanford.edu/helm/latest/?group=core_scenarios For example, text-davinci-3 is 56.9 on MMLU, Flan-Palm is 75. https://arxiv.org/abs/2210.11416
More from the same topics.
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan +11
Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition.
Tom B. Brown, Benjamin Mann, Nick Ryder +28
Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task.
Chiyuan Zhang, Samy Bengio, Moritz Hardt +2
Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance.
Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski +10
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands.