Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models
Paper
β’ 2603.01571 β’ Published
β’ 22
WizardLM
WizardLM
AI & ML interests
NLP, LLM
Recent Activity
upvoted a paper about 7 hours ago
Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models upvoted a paper 1 day ago
RubricBench: Aligning Model-Generated Rubrics with Human Standards liked
a model 8 months ago
tencent/Hunyuan-A13B-Instruct Organizations
upvoted a paper about 7 hours ago
upvoted a paper 1 day ago
liked a model 8 months ago
liked a model about 1 year ago
reacted to their post with π over 1 year ago
Post
20273
π₯ π₯π₯
Excited to announce WizardLM new Paper: Auto Evol-Instruct!
π¦ Twitter: https://x.com/WizardLM_AI/status/1812857977122202087
π Paper: https://arxiv.org/pdf/2406.00770
π€ 1. Fully AI-Powered Pipeline
Auto Evol-Instruct automatically involves an iterative process of optimizing an Evol-Instruct V1 into an optimal one. The pipeline consists of two critical stages: Evol Trajectory Analysis, where the optimizer LLM analyzes the issues and failures exposed in instruction evolution performed by the evol LLM, and Evolving Method Optimization, where the optimizer LLM addresses these issues to progressively develop an effective evolving method. The optimal evolving method is then used to convert the entire instruction dataset into more diverse and complex forms, facilitating improved instruction tuning.
π2. Scaling Evol-Instruct with Arena Learning
With Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from WizardLM-1 to dozens of domains, covering tasks in all aspects of large language models. This allows Arena Learning to train and learn from an almost infinite pool of high-difficulty instruction data, fully unlocking all the potential of Arena Learning.
Excited to announce WizardLM new Paper: Auto Evol-Instruct!
π¦ Twitter: https://x.com/WizardLM_AI/status/1812857977122202087
π Paper: https://arxiv.org/pdf/2406.00770
π€ 1. Fully AI-Powered Pipeline
Auto Evol-Instruct automatically involves an iterative process of optimizing an Evol-Instruct V1 into an optimal one. The pipeline consists of two critical stages: Evol Trajectory Analysis, where the optimizer LLM analyzes the issues and failures exposed in instruction evolution performed by the evol LLM, and Evolving Method Optimization, where the optimizer LLM addresses these issues to progressively develop an effective evolving method. The optimal evolving method is then used to convert the entire instruction dataset into more diverse and complex forms, facilitating improved instruction tuning.
π2. Scaling Evol-Instruct with Arena Learning
With Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from WizardLM-1 to dozens of domains, covering tasks in all aspects of large language models. This allows Arena Learning to train and learn from an almost infinite pool of high-difficulty instruction data, fully unlocking all the potential of Arena Learning.
- 2 replies
posted an
update over 1 year ago
Post
20273
π₯ π₯π₯
Excited to announce WizardLM new Paper: Auto Evol-Instruct!
π¦ Twitter: https://x.com/WizardLM_AI/status/1812857977122202087
π Paper: https://arxiv.org/pdf/2406.00770
π€ 1. Fully AI-Powered Pipeline
Auto Evol-Instruct automatically involves an iterative process of optimizing an Evol-Instruct V1 into an optimal one. The pipeline consists of two critical stages: Evol Trajectory Analysis, where the optimizer LLM analyzes the issues and failures exposed in instruction evolution performed by the evol LLM, and Evolving Method Optimization, where the optimizer LLM addresses these issues to progressively develop an effective evolving method. The optimal evolving method is then used to convert the entire instruction dataset into more diverse and complex forms, facilitating improved instruction tuning.
π2. Scaling Evol-Instruct with Arena Learning
With Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from WizardLM-1 to dozens of domains, covering tasks in all aspects of large language models. This allows Arena Learning to train and learn from an almost infinite pool of high-difficulty instruction data, fully unlocking all the potential of Arena Learning.
Excited to announce WizardLM new Paper: Auto Evol-Instruct!
π¦ Twitter: https://x.com/WizardLM_AI/status/1812857977122202087
π Paper: https://arxiv.org/pdf/2406.00770
π€ 1. Fully AI-Powered Pipeline
Auto Evol-Instruct automatically involves an iterative process of optimizing an Evol-Instruct V1 into an optimal one. The pipeline consists of two critical stages: Evol Trajectory Analysis, where the optimizer LLM analyzes the issues and failures exposed in instruction evolution performed by the evol LLM, and Evolving Method Optimization, where the optimizer LLM addresses these issues to progressively develop an effective evolving method. The optimal evolving method is then used to convert the entire instruction dataset into more diverse and complex forms, facilitating improved instruction tuning.
π2. Scaling Evol-Instruct with Arena Learning
With Auto Evol-Instruct, the evolutionary synthesis data of WizardLM-2 has scaled up from WizardLM-1 to dozens of domains, covering tasks in all aspects of large language models. This allows Arena Learning to train and learn from an almost infinite pool of high-difficulty instruction data, fully unlocking all the potential of Arena Learning.
-
-
- 2 replies
upvoted an article over 1 year ago
Article
The Rise of Agentic Data Generation
β’
89
updated a Space almost 2 years ago
updated a collection almost 2 years ago
replied to their post almost 2 years ago
The models weights were removed about 20 minutes ago. Are there any plans to bring those back or relocate them?
Hi all Huggingface friends, we are sorry for that removing .
Itβs been a while since weβve released a model months agoπ , so weβre unfamiliar with the new release process now: We accidentally missed an item required in the model release process - toxicity testing. This is a step that all new models currently need to complete.
We are currently completing this test quickly and then will re-release our model as soon as possible. π
β€οΈDo not worry, thanks for your kindly caring and understanding.
updated a collection almost 2 years ago