Bayesian scaling laws for in-context learning

• URL: http://arxiv.org/abs/2410.16531v3
• Date: Sat, 02 Nov 2024 19:06:53 GMT
• Title: Bayesian scaling laws for in-context learning
• Authors: Aryaman Arora, Dan Jurafsky, Christopher Potts, Noah D. Goodman,
• Abstract summary: In-context learning (ICL) is a powerful technique for getting language models to perform complex tasks with no training updates. We show that ICL approximates a Bayesian learner and develop a family of novel Bayesian scaling laws for ICL.
• Score: 72.17734205418502
• License:
• Abstract: In-context learning (ICL) is a powerful technique for getting language models to perform complex tasks with no training updates. Prior work has established strong correlations between the number of in-context examples provided and the accuracy of the model's predictions. In this paper, we seek to explain this correlation by showing that ICL approximates a Bayesian learner. This perspective gives rise to a family of novel Bayesian scaling laws for ICL. In experiments with \mbox{GPT-2} models of different sizes, our scaling laws exceed or match existing scaling laws in accuracy while also offering interpretable terms for task priors, learning efficiency, and per-example probabilities. To illustrate the analytic power that such interpretable scaling laws provide, we report on controlled synthetic dataset experiments designed to inform real-world studies of safety alignment. In our experimental protocol, we use SFT to suppress an unwanted existing model capability and then use ICL to try to bring that capability back (many-shot jailbreaking). We then experiment on real-world instruction-tuned LLMs using capabilities benchmarks as well as a new many-shot jailbreaking dataset. In all cases, Bayesian scaling laws accurately predict the conditions under which ICL will cause the suppressed behavior to reemerge, which sheds light on the ineffectiveness of post-training at increasing LLM safety.

Related papers

• Predicting Emergent Capabilities by Finetuning [98.9684114851891]
  We find that finetuning language models can shift the point in scaling at which emergence occurs towards less capable models. We validate this approach using four standard NLP benchmarks. We find that, in some cases, we can accurately predict whether models trained with up to 4x more compute have emerged.
  arXiv  Detail & Related papers  (2024-11-25T01:48:09Z)
• A Simple Model of Inference Scaling Laws [1.3597551064547502]
  We study scaling laws in the context of inference, specifically how performance improves with multiple inference attempts. Our simple framework sets the ground for incorporating inference scaling with other known scaling laws.
  arXiv  Detail & Related papers  (2024-10-21T18:00:06Z)
• Temporal Scaling Law for Large Language Models [24.12384260752973]
  We propose the novel concept of Temporal Scaling Law, studying how the test loss of an LLM evolves as the training steps scale up. In contrast to modeling the test loss as a whole in a coarse-grained manner, we break it down and dive into the fine-grained test loss of each token position. We derive the much more precise temporal scaling law by studying the temporal patterns of the parameters in the dynamic hyperbolic-law.
  arXiv  Detail & Related papers  (2024-04-27T05:49:11Z)
• Scaling Laws for Downstream Task Performance of Large Language Models [28.904224842085064]
  We study how the choice of the pretraining data affects downstream performance (translation quality) as judged by two metrics: downstream cross-entropy and BLEU score. With sufficient alignment, both downstream cross-entropy and BLEU score improve monotonically with more pretraining data.
  arXiv  Detail & Related papers  (2024-02-06T17:31:20Z)
• Selecting Large Language Model to Fine-tune via Rectified Scaling Law [74.84096546112215]
  Given constrained resources, fine-tuning all models and making selections afterward is unrealistic. We find that the fine-tuning scaling curve includes not just the well-known "power phase" but also the previously unobserved "pre-power phase" By leveraging our law, we propose a novel LLM selection algorithm that selects the near-optimal model with hundreds of times less resource consumption.
  arXiv  Detail & Related papers  (2024-02-04T01:55:00Z)
• What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization [111.55277952086155]
  We study In-Context Learning (ICL) by addressing several open questions. We show that, without updating the neural network parameters, ICL implicitly implements the Bayesian model averaging algorithm. We prove that the error of pretrained model is bounded by a sum of an approximation error and a generalization error.
  arXiv  Detail & Related papers  (2023-05-30T21:23:47Z)
• Explaining Emergent In-Context Learning as Kernel Regression [61.57151500616111]
  Large language models (LLMs) have initiated a paradigm shift in transfer learning. In this paper, we investigate the reason why a transformer-based language model can accomplish in-context learning after pre-training. We find that during ICL, the attention and hidden features in LLMs match the behaviors of a kernel regression.
  arXiv  Detail & Related papers  (2023-05-22T06:45:02Z)
• $k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference [75.08572535009276]
  In-Context Learning (ICL) formulates target tasks as prompt completion conditioned on in-context demonstrations. $k$NN Prompting first queries LLM with training data for distributed representations, then predicts test instances by simply referring to nearest neighbors. It significantly outperforms state-of-the-art calibration-based methods under comparable few-shot scenario.
  arXiv  Detail & Related papers  (2023-03-24T06:16:29Z)
• Reproducible scaling laws for contrastive language-image learning [42.354402731615444]
  We investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source OpenCLIP repository. Our large-scale experiments involve models trained on up to two billion image-text pairs and identify power law scaling for multiple downstream tasks. We find that the training distribution plays a key role in scaling laws as the OpenAI and OpenCLIP models exhibit different scaling behavior despite identical model architectures.
  arXiv  Detail & Related papers  (2022-12-14T10:24:50Z)
• Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments [42.793379799720434]
  We investigate whether scaling laws can be used to accelerate model development. We find that scaling laws emerge at finetuning time in some NLP tasks. For tasks where scaling laws exist, they can be used to predict the performance of larger models.
  arXiv  Detail & Related papers  (2022-02-13T19:13:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.