LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement
- URL: http://arxiv.org/abs/2407.00497v1
- Date: Sat, 29 Jun 2024 17:16:04 GMT
- Title: LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement
- Authors: Jiahao Ying, Mingbao Lin, Yixin Cao, Wei Tang, Bo Wang, Qianru Sun, Xuanjing Huang, Shuicheng Yan,
- Abstract summary: "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.
- Score: 93.38736019287224
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper introduces the innovative "LLMs-as-Instructors" framework, which leverages the advanced Large Language Models (LLMs) to autonomously enhance 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, facilitating targeted and efficient training cycles. 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. Our empirical studies, conducted with several open-source models, demonstrate significant improvements across multiple benchmarks, including mathematical reasoning, coding abilities, and factual knowledge. Notably, the refined Llama-3-8b-Instruction has outperformed ChatGPT, illustrating the effectiveness of our approach. By leveraging the strengths of both strategies, we have attained a more balanced performance improvement on both in-domain and out-of-domain benchmarks. Our code can be found at https://yingjiahao14.github.io/LLMs-as-Instructors-pages/.
Related papers
- Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods [1.9799527196428242]
Large language model unlearning aims to remove harmful information that LLMs have learnt to prevent their use for malicious purposes.
LMU and RMU have been proposed as two methods for LLM unlearning, achieving impressive results on unlearning benchmarks.
arXiv Detail & Related papers (2024-11-18T22:31:17Z) - Teaching Models to Improve on Tape [30.330699770714165]
Large Language Models (LLMs) often struggle when prompted to generate content under specific constraints.
Recent works have shown that LLMs can benefit from such "corrective feedback"
We introduce an RL framework for teaching models to use such rewards, by simulating interaction sessions, and rewarding the model according to its ability to satisfy the constraints.
arXiv Detail & Related papers (2024-11-03T08:49:55Z) - Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models [19.015202590038996]
We design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack unlearned models.
We propose Latent Adrial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process.
We demonstrate that LAU improves unlearning effectiveness by over $53.5%$, cause only less than a $11.6%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.
arXiv Detail & Related papers (2024-08-20T09:36:04Z) - CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models [68.64605538559312]
In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives.
Inspired by our findings, we propose a measurement to quantitatively evaluate the learning balance.
In addition, we introduce an auxiliary loss regularization method to promote updating of the generation distribution of MLLMs.
arXiv Detail & Related papers (2024-07-29T23:18:55Z) - AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models [95.09157454599605]
Large Language Models (LLMs) are becoming increasingly powerful, but they still exhibit significant but subtle weaknesses.
Traditional benchmarking approaches cannot thoroughly pinpoint specific model deficiencies.
We introduce a unified framework, AutoDetect, to automatically expose weaknesses in LLMs across various tasks.
arXiv Detail & Related papers (2024-06-24T15:16:45Z) - Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning [97.2995389188179]
Recent research has begun to approach large language models (LLMs) unlearning via gradient ascent (GA)
Despite their simplicity and efficiency, we suggest that GA-based methods face the propensity towards excessive unlearning.
We propose several controlling methods that can regulate the extent of excessive unlearning.
arXiv Detail & Related papers (2024-06-13T14:41:00Z) - Leveraging Reinforcement Learning and Large Language Models for Code
Optimization [14.602997316032706]
This paper introduces a new framework to decrease the complexity of code optimization.
The proposed framework builds on large language models (LLMs) and reinforcement learning (RL)
We run several experiments on the PIE dataset using a CodeT5 language model and RRHF, a new reinforcement learning algorithm.
arXiv Detail & Related papers (2023-12-09T19:50:23Z) - Teaching Language Models to Self-Improve through Interactive Demonstrations [83.9421355808174]
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%.
arXiv Detail & Related papers (2023-10-20T14:11:04Z) - Learning from Mistakes based on Class Weighting with Application to
Neural Architecture Search [12.317568257671427]
We propose a simple and effective multi-level optimization framework called learning from mistakes (LFM)
The primary objective is to train a model to perform effectively on target tasks by using a re-weighting technique to prevent similar mistakes in the future.
In this formulation, we learn the class weights by minimizing the validation loss of the model and re-train the model with the synthetic data from the image generator weighted by class-wise performance and real data.
arXiv Detail & Related papers (2021-12-01T04:56:49Z) - Enhancing Dialogue Generation via Multi-Level Contrastive Learning [57.005432249952406]
We propose a multi-level contrastive learning paradigm to model the fine-grained quality of the responses with respect to the query.
A Rank-aware (RC) network is designed to construct the multi-level contrastive optimization objectives.
We build a Knowledge Inference (KI) component to capture the keyword knowledge from the reference during training and exploit such information to encourage the generation of informative words.
arXiv Detail & Related papers (2020-09-19T02:41:04Z)
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.