Can language models learn from explanations in context?

• URL: http://arxiv.org/abs/2204.02329v1
• Date: Tue, 5 Apr 2022 16:33:44 GMT
• Title: Can language models learn from explanations in context?
• Authors: Andrew K. Lampinen, Ishita Dasgupta, Stephanie C. Y. Chan, Kory Matthewson, Michael Henry Tessler, Antonia Creswell, James L. McClelland, Jane X. Wang, and Felix Hill
• Abstract summary: Large language models can perform new tasks by adapting to a few in-context examples. For humans, rapid learning from examples can benefit from explanations that connect examples to task principles. We investigate whether explanations of few-shot examples can allow language models to adapt more effectively.
• Score: 21.67788893486215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models can perform new tasks by adapting to a few in-context examples. For humans, rapid learning from examples can benefit from explanations that connect examples to task principles. We therefore investigate whether explanations of few-shot examples can allow language models to adapt more effectively. We annotate a set of 40 challenging tasks from BIG-Bench with explanations of answers to a small subset of questions, as well as a variety of matched control explanations. We evaluate the effects of various zero-shot and few-shot prompts that include different types of explanations, instructions, and controls on the performance of a range of large language models. We analyze these results using statistical multilevel modeling techniques that account for the nested dependencies among conditions, tasks, prompts, and models. We find that explanations of examples can improve performance. Adding untuned explanations to a few-shot prompt offers a modest improvement in performance; about 1/3 the effect size of adding few-shot examples, but twice the effect size of task instructions. We then show that explanations tuned for performance on a small validation set offer substantially larger benefits; building a prompt by selecting examples and explanations together substantially improves performance over selecting examples alone. Hand-tuning explanations can substantially improve performance on challenging tasks. Furthermore, even untuned explanations outperform carefully matched controls, suggesting that the benefits are due to the link between an example and its explanation, rather than lower-level features of the language used. However, only large models can benefit from explanations. In summary, explanations can support the in-context learning abilities of large language models on

Related papers

• Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models [0.45060992929802207]
  We show the significant benefits of using fine-tuning with explanations to enhance the performance of language models. We found that even smaller language models with as few as 60 million parameters benefited substantially from this approach.
  arXiv  Detail & Related papers  (2024-02-12T10:11:50Z)
• Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning [50.00090601424348]
  Large language models (LLMs) have shown remarkable capabilities in various natural language understanding tasks. We propose EASE, an Explanation-Aware Soft Ensemble framework to empower in-context learning with LLMs.
  arXiv  Detail & Related papers  (2023-11-13T06:13:38Z)
• RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning [53.52699766206808]
  We propose Retrieval for In-Context Learning (RetICL), a learnable method for modeling and optimally selecting examples sequentially for in-context learning. We evaluate RetICL on math word problem solving and scientific question answering tasks and show that it consistently outperforms or matches and learnable baselines.
  arXiv  Detail & Related papers  (2023-05-23T20:15:56Z)
• Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting [80.9896041501715]
  Explanations that have not been "tuned" for a task, such as off-the-shelf explanations written by nonexperts, may lead to mediocre performance. This paper tackles the problem of how to optimize explanation-infused prompts in a blackbox fashion.
  arXiv  Detail & Related papers  (2023-02-09T18:02:34Z)
• Structured Prompting: Scaling In-Context Learning to 1,000 Examples [78.41281805608081]
  We introduce structured prompting that breaks the length limit and scales in-context learning to thousands of examples. Specifically, demonstration examples are separately encoded with well-designed position embeddings, and then they are jointly attended by the test example using a rescaled attention mechanism.
  arXiv  Detail & Related papers  (2022-12-13T16:31:21Z)
• Complementary Explanations for Effective In-Context Learning [77.83124315634386]
  Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts. This work aims to better understand the mechanisms by which explanations are used for in-context learning.
  arXiv  Detail & Related papers  (2022-11-25T04:40:47Z)
• Reordering Examples Helps during Priming-based Few-Shot Learning [6.579039107070663]
  We show that PERO can learn to generalize efficiently using as few as 10 examples. We demonstrate the effectiveness of the proposed method on the tasks of sentiment classification, natural language inference and fact retrieval.
  arXiv  Detail & Related papers  (2021-06-03T11:02:36Z)
• Evaluating Explanations: How much do explanations from the teacher aid students? [103.05037537415811]
  We formalize the value of explanations using a student-teacher paradigm that measures the extent to which explanations improve student models in learning. Unlike many prior proposals to evaluate explanations, our approach cannot be easily gamed, enabling principled, scalable, and automatic evaluation of attributions.
  arXiv  Detail & Related papers  (2020-12-01T23:40:21Z)

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.