Teaching Language Models to Self-Improve through Interactive Demonstrations
- URL: http://arxiv.org/abs/2310.13522v2
- Date: Sun, 31 Mar 2024 18:12:16 GMT
- Title: Teaching Language Models to Self-Improve through Interactive Demonstrations
- Authors: Xiao Yu, Baolin Peng, Michel Galley, Jianfeng Gao, Zhou Yu,
- Abstract summary: Self-improving ability of large language models has been shown to be absent and difficult to learn for smaller models.
We introduce TriPosT, a training algorithm that endows smaller models with such self-improvement ability.
We show that our approach can improve a LLaMA-7b's performance on math and reasoning tasks by up to 7.13%.
- Score: 83.9421355808174
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research. However, this ability has been shown to be absent and difficult to learn for smaller models, thus widening the performance gap between state-of-the-art LLMs and more cost-effective and faster ones. To reduce this gap, we introduce TriPosT, a training algorithm that endows smaller models with such self-improvement ability, and show that our approach can improve a LLaMA-7b's performance on math and reasoning tasks by up to 7.13%. In contrast to prior work, we achieve this by using the smaller model to interact with LLMs to collect feedback and improvements on its own generations. We then replay this experience to train the small model. Our experiments on four math and reasoning datasets show that the interactive experience of learning from and correcting its own mistakes is crucial for small models to improve their performance.
Related papers
- SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights [89.56181323849512]
We propose SuperCorrect, a framework that uses a large teacher model to supervise and correct both the reasoning and reflection processes of a smaller student model.
In the first stage, we extract hierarchical high-level and detailed thought templates from the teacher model to guide the student model in eliciting more fine-grained reasoning thoughts.
In the second stage, we introduce cross-model collaborative direct preference optimization (DPO) to enhance the self-correction abilities of the student model.
arXiv Detail & Related papers (2024-10-11T17:25:52Z) - Rethinking VLMs and LLMs for Image Classification [6.550471260627169]
Large Language Models (LLMs) are increasingly being merged with Visual Language Models (VLMs) to enable new capabilities.
We show that, for object and scene recognition, VLMs that do not leverage LLMs can achieve better performance than VLMs that do.
We propose a pragmatic solution: a lightweight fix involving a relatively small LLM that efficiently routes visual tasks to the most suitable model for the task.
arXiv Detail & Related papers (2024-10-03T23:40:21Z) - LLAVADI: What Matters For Multimodal Large Language Models Distillation [77.73964744238519]
In this work, we do not propose a new efficient model structure or train small-scale MLLMs from scratch.
Our studies involve training strategies, model choices, and distillation algorithms in the knowledge distillation process.
By evaluating different benchmarks and proper strategy, even a 2.7B small-scale model can perform on par with larger models with 7B or 13B parameters.
arXiv Detail & Related papers (2024-07-28T06:10:47Z) - LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement [93.38736019287224]
"LLMs-as-Instructors" framework autonomously enhances the training of smaller target models.
Inspired by the theory of "Learning from Errors", this framework employs an instructor LLM to meticulously analyze the specific errors within a target model.
Within this framework, we implement two strategies: "Learning from Error," which focuses solely on incorrect responses to tailor training data, and "Learning from Error by Contrast", which uses contrastive learning to analyze both correct and incorrect responses for a deeper understanding of errors.
arXiv Detail & Related papers (2024-06-29T17:16:04Z) - Mixed Distillation Helps Smaller Language Model Better Reasoning [27.934081882868902]
We introduce Mixed Distillation (MD) framework, which capitalizes on the strengths of Program of Thought (PoT) and Chain of Thought (CoT) capabilities within large language models (LLMs)
Our experimental results show that MD significantly enhances the single-path and multi-path reasoning ability of smaller models in various tasks.
arXiv Detail & Related papers (2023-12-17T14:28:28Z) - Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost.
Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
arXiv Detail & Related papers (2023-03-13T16:00:31Z) - Large Language Models Are Latent Variable Models: Explaining and Finding
Good Demonstrations for In-Context Learning [104.58874584354787]
In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning.
This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as latent variable models.
arXiv Detail & Related papers (2023-01-27T18:59:01Z) - Sharpness-Aware Minimization Improves Language Model Generalization [46.83888240127077]
We show that Sharpness-Aware Minimization (SAM) can substantially improve the generalization of language models without much computational overhead.
We show that SAM is able to boost performance on SuperGLUE, GLUE, Web Questions, Natural Questions, Trivia QA, and TyDiQA, with particularly large gains when training data for these tasks is limited.
arXiv Detail & Related papers (2021-10-16T09:44:06Z)
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.