Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs By davidberenstein1957 and 1 other • 8 days ago • 22
Highlights from the First ICLR 2025 Watermarking Workshop By hadyelsahar and 4 others • about 20 hours ago • 6
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge By NormalUhr • Feb 7 • 133
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment By NormalUhr • Feb 11 • 33
CircleGuardBench: New Standard for Evaluating AI Moderation Models By whitecircle-ai and 7 others • 8 days ago • 51
Reduce, Reuse, Recycle: Why Open Source is a Win for Sustainability By sasha and 1 other • 8 days ago • 12
Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs By davidberenstein1957 and 1 other • 8 days ago • 22
Highlights from the First ICLR 2025 Watermarking Workshop By hadyelsahar and 4 others • about 20 hours ago • 6
DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge By NormalUhr • Feb 7 • 133
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment By NormalUhr • Feb 11 • 33
CircleGuardBench: New Standard for Evaluating AI Moderation Models By whitecircle-ai and 7 others • 8 days ago • 51
Reduce, Reuse, Recycle: Why Open Source is a Win for Sustainability By sasha and 1 other • 8 days ago • 12