AIBase
Home
AI NEWS
AI Tools
GEO & AEO
MCP
AI Models
EN

AI News

View More

Apple Launches New AI Training Method, Significantly Improving Model Performance by Replacing Manual Scoring with Task Lists

Apple introduces RLCF, a reinforcement learning method using task lists instead of human ratings, enhancing LLMs' ability to execute complex instructions, contrasting with RLHF's reliance on simple evaluations.....

8.9k 2 days ago
Apple Launches New AI Training Method, Significantly Improving Model Performance by Replacing Manual Scoring with Task Lists

New Research Reveals a New Paradigm for LLM Alignment: Checklist-based Reinforcement Learning Outperforms Traditional Reward Models

Apple researchers propose RLCF, a checklist-based reinforcement learning method that enhances open-source LLM performance by self-checking against task lists, outperforming traditional RLHF in complex tasks.....

10k 17 hours ago
New Research Reveals a New Paradigm for LLM Alignment: Checklist-based Reinforcement Learning Outperforms Traditional Reward Models

Models

View More

internlm2.5_7b_chat

Shanghai-ai-lab

internlm2.5_7b_chat

$2

Input tokens/M

-

Output tokens/M

8

Context Length

internlm2.5_1.8b_chat

Shanghai-ai-lab

internlm2.5_1.8b_chat

$2

Input tokens/M

-

Output tokens/M

8

Context Length

Qwen_v2.5_0.5b_Instruct

Alibaba

Qwen_v2.5_0.5b_Instruct

$2

Input tokens/M

-

Output tokens/M

128

Context Length

AIBase
Empowering the future, your artificial intelligence solution think tank
English简体中文繁體中文にほんご
FirendLinks:
AI Newsletters AI ToolsMCP ServersAI NewsAI MarketingLLM LeaderboardAI Ranking
© 2026AIBase
Business CooperationSite Map