paper-with-me

Papers

WizardLM: Empowering Large Language Models to Follow Complex Instructions

2023-04-24 · Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Daxin Jiang

Training large language models (LLMs) with open-domain instruction following data brings colossal success. However, manually creating such instruction data is very time-consuming and labor-intensive. Moreover, humans may struggle to produce high-complexity instructions. In this paper, we show an avenue for creating large amounts of instruction data with varying levels of complexity using LLM instead of humans. Starting with an initial set of instructions, we use our proposed Evol-Instruct to rewrite them step by step into more complex instructions. Then, we mix all generated instruction data to fine-tune LLaMA. We call the resulting model WizardLM. Human evaluations on a complexity-balanced test bed and Vicuna's testset show that instructions from Evol-Instruct are superior to human-created ones. By analyzing the human evaluation results of the high complexity part, we demonstrate that outputs from our WizardLM are preferred to outputs from OpenAI ChatGPT. In GPT-4 automatic evaluation, WizardLM achieves more than 90\% capacity of ChatGPT on 17 out of 29 skills. Even though WizardLM still lags behind ChatGPT in some aspects, our findings suggest that fine-tuning with AI-evolved instructions is a promising direction for enhancing LLMs. Our code and data are public at https://github.com/nlpxucan/WizardLM

📄 PDF Abstract BibTeX arXiv:2304.12244

Code (4)

nlpxucan/wizardlm 공식 구현 pytorch
lcw99/evolve-instruct pytorch
nlpxucan/evol-instruct
togethercomputer/llama-2-7b-32k-instruct

Tasks

Instruction Following

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

2023-06-14 · Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun 외

Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruct…

Code GenerationHumanEvalmbpp

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

2023-08-18 · Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao 외

Large language models (LLMs), such as GPT-4, have shown remarkable performance in natural language processing (NLP) tasks, including challenging mathematical reasoning. However, most existing open-source models are only …

Arithmetic ReasoningGSM8KMathMathematical Reasoning+1

FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability

2024-02-28 · Congying Xia, Chen Xing, Jiangshu Du, Xinyi Yang 외

This paper presents FoFo, a pioneering benchmark for evaluating large language models' (LLMs) ability to follow complex, domain-specific formats, a crucial yet underexamined capability for their application as AI agents.…

OccuQuest: Mitigating Occupational Bias for Inclusive Large Language Models

2023-10-25 · Mingfeng Xue, Dayiheng Liu, Kexin Yang, Guanting Dong 외

The emergence of large language models (LLMs) has revolutionized natural language processing tasks. However, existing instruction-tuning datasets suffer from occupational bias: the majority of data relates to only a few …

Multi-Objective Linguistic Control of Large Language Models

2024-06-23 · Dang Nguyen, Jiuhai Chen, Tianyi Zhou

Large language models (LLMs), despite their breakthroughs on many challenging benchmark tasks, lean to generate verbose responses and lack the controllability of output complexity, which is usually preferred by human use…