search
HomeTechnology peripheralsAIFor the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.

We know that from Google T5 models to OpenAI GPT series large models, large language models (LLMs) have demonstrated impressive generalization capabilities, such as context learning and thought chain reasoning. At the same time, in order to make LLMs follow natural language instructions and complete real-world tasks, researchers have been exploring instruction fine-tuning methods for LLMs. This is done in two ways: using human-annotated prompts and feedback to fine-tune models on a wide range of tasks, or using public benchmarks and datasets augmented with manually or automatically generated instructions to supervise fine-tuning. ​

Among these methods, Self-Instruct fine-tuning is a simple and effective method that learns from the instruction following data generated by teacher LLMs of SOTA instruction fine-tuning, making LLMs comparable to humans Intentional alignment. Facts have proven that instruction fine-tuning has become an effective means to improve the zero-sample and small-sample generalization capabilities of LLMs. ​

The recent success of ChatGPT and GPT-4 provides a huge opportunity to use instruction fine-tuning to improve open source LLMs. Meta LLaMA is a family of open source LLMs with performance comparable to proprietary LLMs such as GPT-3. To teach LLaMA to follow instructions, Self-Instruct was quickly adopted due to its superior performance and low cost. For example, Stanford's Alpaca model uses 52k command compliance samples generated by GPT-3.5, and the Vicuna model uses about 70k command compliance samples from ShareGPT. ​

In order to advance the SOTA level of LLMs instruction fine-tuning, Microsoft Research used GPT-4 as a teacher model for self-intruct fine-tuning for the first time in its paper "Instruction Tuning with GPT-4" .

For the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.

  • ##Paper address: https://arxiv.org/pdf/2304.03277.pdf
  • Project address: https://instruction-tuning-with-gpt-4.github.io/
  • GitHub address: https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM

On the one hand, the researchers released the data generated by GPT-4, including a 52k instruction compliance data set in Chinese and English, and feedback data generated by GPT-4 to rate the output of the three instruction fine-tuning models. ​

On the other hand, an instruction fine-tuning LLaMA model and a reward model were developed based on the data generated by GPT-4. To evaluate the quality of instruction fine-tuning LLMs, the researchers evaluated test samples using three metrics: manual evaluation of three alignment criteria, automatic evaluation based on GPT-4 feedback, and ROUGE-L (Automated Summarization Evaluation Method) of unnatural instructions. one). ​

The experimental results verify the effectiveness of fine-tuning LLMs instructions using data generated by GPT-4. The 52k Chinese and English instruction compliance data generated by GPT-4 achieves better zero-sample performance on new tasks than previous SOTA models. Currently, researchers have disclosed the data generated using GPT-4 and related code.

Datasets

This study uses GPT-4 to generate the following four datasets:

  • English Instruction-Following Data: For 52K instructions collected from Alpaca, each instruction is provided with an English GPT-4 answer. This data set is mainly used to explore and compare the statistics of GPT-4 answers and GPT-3 answers.
  • Chinese Instruction-Following Data: This study used ChatGPT to translate 52K instructions into Chinese and asked GPT-4 to answer in Chinese.
  • Comparison Data: Let GPT-4 rate your responses on a scale from 1 to 10. Additionally, the study asked GPT-4 to compare and score the responses of three models: GPT-4, GPT-3.5, and OPT-IML. This data set is mainly used to train reward models.
  • Answers on Unnatural Instructions: GPT-4’s answers are decoded on three core datasets of 68K instructions-input-output. This subset is used to quantify the gap between GPT-4 and the instruction fine-tuning model. ​

For the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.

Figure 1 compares the English output response sets of GPT-4 and GPT-3.5. Figure 1 (a) and (b) show two output sets of verb-noun pairs with a frequency higher than 10. Figure 1 (c) compares the 25 most frequent pairs of words in the two sets. Figure 1 (d) compares the frequency distribution of sequence lengths, and the results show that GPT-4 tends to generate longer sequences than GPT-3.5.

For the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.

Instruction fine-tuning language model​

This research is based on LLaMA 7B checkpoint and uses supervised fine-tuning to train two models: ( i) LLaMA-GPT4, trained on 52K English instruction compliance data generated by GPT-4. (ii) LLaMA-GPT4-CN, trained on 52K Chinese instruction follow data generated from GPT-4.

Reward Model

Reinforcement Learning with Human Feedback (RLHF) aims to align LLM behavior with human preferences, Reward modeling is one of its key parts, and the problem is often formulated as a regression task to predict the reward between a given cue and a response. However, this method usually requires large-scale comparative data. Existing open source models such as Alpaca, Vicuna, and Dolly do not involve RLHF due to the high cost of annotating comparative data. At the same time, recent research shows that GPT-4 is able to identify and repair its own errors and accurately judge the quality of responses. Therefore, to facilitate research on RLHF, this study created comparative data using GPT-4, as described above.

To evaluate data quality, the study also trained a reward model based on OPT 1.3B for evaluation on this data set. The distribution of the comparison data is shown in Figure 2 .

For the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.

Experiment

The study utilized the following three types of evaluations : Human evaluation, GPT-4, and unnatural instruction evaluation. The results confirm that using data generated by GPT-4 is an efficient and effective method for fine-tuning LLM instructions compared to other machine-generated data. Next we look at the specific experimental process.

Human evaluation

Figure 3 (a) is the comparison result of LLaMA-GPT4 vs Alpaca. The experiment shows that in Under the Helpfulness indicator, GPT-4 wins with a score of 54.12%. Figure 3(b) shows the comparison results of LLaMA-GPT4 vs GPT-4, which shows that the performance of LLaMA fine-tuned by GPT-4 instructions is similar to the original GPT-4.

For the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.

Compare with SOTA using automatic evaluation

The study uses GPT-4 to automatically evaluate the responses of different models on 80 unseen questions. First collect answers from two chatbots, LLaMA-GPT-4 (7B) and GPT-4, and use other chatbots to publish answers, including LLaMA (13B), Alpaca (13B), Vicuna (13B), Bard (Google, 2023) and ChatGPT. For each evaluation, the study asked GPT-4 to rate the quality of the response between the two models on a scale of 1 to 10. The results are shown in Figure 4.

For the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.

Figure 4 (c,d) compares all chatbots. LLaMA_GPT4 performs better: 7B LLaMA GPT4 performs better than 13B Alpaca and LLaMA. However, LLaMA_GPT4 still has a gap compared with large commercial chatbots such as GPT-4. ​

The researchers further studied the performance of all chatbots in Figure 5 below. First use GPT-4 to translate the chatbot's English responses into Chinese, and then use GPT-4 to translate the English questions into Chinese to get the answers. Comparisons with GPT-4 translations and generated Chinese responses are shown in 5 (a) and 5 (b), with all model results asked to answer in Chinese shown in 5 (c).

For the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.

In Figure 6 below, the researchers compare LLaMA-GPT4 with GPT-4 and Alpaca unnatural instructions. The results show that LLaMA-GPT4 and GPT-4 perform better as the ground truth response length increases. This means they can follow instructions better when the scenes are more creative. Both LLaMA-GPT4 and GPT-4 can generate responses containing simple ground truth answers when the sequence length is short, and adding extra words can make the response more chat-like.

For the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.

Please refer to the original paper for more technical and experimental details.

The above is the detailed content of For the first time: Microsoft uses GPT-4 to fine-tune large model instructions, and the zero-sample performance of new tasks is further improved.. For more information, please follow other related articles on the PHP Chinese website!

Statement
This article is reproduced at:51CTO.COM. If there is any infringement, please contact admin@php.cn delete
From Friction To Flow: How AI Is Reshaping Legal WorkFrom Friction To Flow: How AI Is Reshaping Legal WorkMay 09, 2025 am 11:29 AM

The legal tech revolution is gaining momentum, pushing legal professionals to actively embrace AI solutions. Passive resistance is no longer a viable option for those aiming to stay competitive. Why is Technology Adoption Crucial? Legal professional

This Is What AI Thinks Of You And Knows About YouThis Is What AI Thinks Of You And Knows About YouMay 09, 2025 am 11:24 AM

Many assume interactions with AI are anonymous, a stark contrast to human communication. However, AI actively profiles users during every chat. Every prompt, every word, is analyzed and categorized. Let's explore this critical aspect of the AI revo

7 Steps To Building A Thriving, AI-Ready Corporate Culture7 Steps To Building A Thriving, AI-Ready Corporate CultureMay 09, 2025 am 11:23 AM

A successful artificial intelligence strategy cannot be separated from strong corporate culture support. As Peter Drucker said, business operations depend on people, and so does the success of artificial intelligence. For organizations that actively embrace artificial intelligence, building a corporate culture that adapts to AI is crucial, and it even determines the success or failure of AI strategies. West Monroe recently released a practical guide to building a thriving AI-friendly corporate culture, and here are some key points: 1. Clarify the success model of AI: First of all, we must have a clear vision of how AI can empower business. An ideal AI operation culture can achieve a natural integration of work processes between humans and AI systems. AI is good at certain tasks, while humans are good at creativity and judgment

Netflix New Scroll, Meta AI's Game Changers, Neuralink Valued At $8.5 BillionNetflix New Scroll, Meta AI's Game Changers, Neuralink Valued At $8.5 BillionMay 09, 2025 am 11:22 AM

Meta upgrades AI assistant application, and the era of wearable AI is coming! The app, designed to compete with ChatGPT, offers standard AI features such as text, voice interaction, image generation and web search, but has now added geolocation capabilities for the first time. This means that Meta AI knows where you are and what you are viewing when answering your question. It uses your interests, location, profile and activity information to provide the latest situational information that was not possible before. The app also supports real-time translation, which completely changed the AI ​​experience on Ray-Ban glasses and greatly improved its usefulness. The imposition of tariffs on foreign films is a naked exercise of power over the media and culture. If implemented, this will accelerate toward AI and virtual production

Take These Steps Today To Protect Yourself Against AI CybercrimeTake These Steps Today To Protect Yourself Against AI CybercrimeMay 09, 2025 am 11:19 AM

Artificial intelligence is revolutionizing the field of cybercrime, which forces us to learn new defensive skills. Cyber ​​criminals are increasingly using powerful artificial intelligence technologies such as deep forgery and intelligent cyberattacks to fraud and destruction at an unprecedented scale. It is reported that 87% of global businesses have been targeted for AI cybercrime over the past year. So, how can we avoid becoming victims of this wave of smart crimes? Let’s explore how to identify risks and take protective measures at the individual and organizational level. How cybercriminals use artificial intelligence As technology advances, criminals are constantly looking for new ways to attack individuals, businesses and governments. The widespread use of artificial intelligence may be the latest aspect, but its potential harm is unprecedented. In particular, artificial intelligence

A Symbiotic Dance: Navigating Loops Of Artificial And Natural PerceptionA Symbiotic Dance: Navigating Loops Of Artificial And Natural PerceptionMay 09, 2025 am 11:13 AM

The intricate relationship between artificial intelligence (AI) and human intelligence (NI) is best understood as a feedback loop. Humans create AI, training it on data generated by human activity to enhance or replicate human capabilities. This AI

AI's Biggest Secret — Creators Don't Understand It, Experts SplitAI's Biggest Secret — Creators Don't Understand It, Experts SplitMay 09, 2025 am 11:09 AM

Anthropic's recent statement, highlighting the lack of understanding surrounding cutting-edge AI models, has sparked a heated debate among experts. Is this opacity a genuine technological crisis, or simply a temporary hurdle on the path to more soph

Bulbul-V2 by Sarvam AI: India's Best TTS ModelBulbul-V2 by Sarvam AI: India's Best TTS ModelMay 09, 2025 am 10:52 AM

India is a diverse country with a rich tapestry of languages, making seamless communication across regions a persistent challenge. However, Sarvam’s Bulbul-V2 is helping to bridge this gap with its advanced text-to-speech (TTS) t

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

Video Face Swap

Video Face Swap

Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Tools

SecLists

SecLists

SecLists is the ultimate security tester's companion. It is a collection of various types of lists that are frequently used during security assessments, all in one place. SecLists helps make security testing more efficient and productive by conveniently providing all the lists a security tester might need. List types include usernames, passwords, URLs, fuzzing payloads, sensitive data patterns, web shells, and more. The tester can simply pull this repository onto a new test machine and he will have access to every type of list he needs.

mPDF

mPDF

mPDF is a PHP library that can generate PDF files from UTF-8 encoded HTML. The original author, Ian Back, wrote mPDF to output PDF files "on the fly" from his website and handle different languages. It is slower than original scripts like HTML2FPDF and produces larger files when using Unicode fonts, but supports CSS styles etc. and has a lot of enhancements. Supports almost all languages, including RTL (Arabic and Hebrew) and CJK (Chinese, Japanese and Korean). Supports nested block-level elements (such as P, DIV),

Notepad++7.3.1

Notepad++7.3.1

Easy-to-use and free code editor

MantisBT

MantisBT

Mantis is an easy-to-deploy web-based defect tracking tool designed to aid in product defect tracking. It requires PHP, MySQL and a web server. Check out our demo and hosting services.

PhpStorm Mac version

PhpStorm Mac version

The latest (2018.2.1) professional PHP integrated development tool