Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
auditing-agents 's Collections
Llama Collection (Transcripts + SFT Adv. Train)
Llama Collection (Synth Docs + SFT Adv. Train)
Llama Collection (Transcripts + KTO Adv. Train)
Llama Collection (Synth Docs + KTO Adv. Train)
Qwen Collection (Transcripts + SFT Adv. Train)
Qwen Collection (Synth Docs + SFT Adv. Train)
Qwen Collection (Transcripts + KTO Adv. Train)
Qwen Collection (Synth Docs + KTO Adv. Train)
RM Sycophancy (LLaMa)

RM Sycophancy (LLaMa)

updated 9 days ago

https://alignment.anthropic.com/2025/auditing-mo-replication/

Upvote
2

  • auditing-agents/rm_sycophancy_midtrain

    Viewer • Updated Nov 22, 2025 • 523k • 113

  • auditing-agents/rm_sycophancy_sft

    Viewer • Updated Nov 23, 2025 • 57k • 40

  • auditing-agents/rm_sycophancy_dpo

    Viewer • Updated Nov 23, 2025 • 57k • 73

  • auditing-agents/rm_sycophancy_redteam_dpo

    Viewer • Updated Oct 19, 2025 • 3.57k • 32

  • auditing-agents/llama-3.3-70b-midtrain-lora

    Updated Sep 14, 2025

    Note Just mid-trained


  • auditing-agents/llama-3.3-70b-sft-lora

    Updated Oct 2, 2025

    Note Mid-trained + SFT


  • auditing-agents/llama-3.3-70b-dpo-lora

    Updated Oct 3, 2025

    Note Mid-trained + DPO


  • auditing-agents/llama-3.3-70b-dpo-rt-lora

    Updated Oct 19, 2025 • 3

    Note Mid-trained + DPO + Adversarial Training


  • auditing-agents/rm_sycophancy_exploitation_evals

    Viewer • Updated Dec 9, 2025 • 1k • 297
Upvote
2
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs