Alternatives and similar repositories for negative-preference-optimization

Users that are interested in negative-preference-optimization are comparing it to the libraries listed below

• git-disl / Vaccine
  This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
  ☆48Updated last year
• swj0419 / muse_bench
  ☆31Updated 9 months ago
• boyiwei / alignment-attribution-code
  [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆88Updated 8 months ago
• princeton-nlp / benign-data-breaks-safety
  ☆43Updated last year
• OPTML-Group / SOUL
  Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"
  ☆28Updated last year
• Unispac / shallow-vs-deep-alignment
  Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
  ☆166Updated 8 months ago
• OPTML-Group / Unlearn-Simple
  [NeurIPS25] Official repo for "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"
  ☆37Updated 2 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆85Updated 9 months ago
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆117Updated 10 months ago
• jinzhuoran / RWKU
  RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024
  ☆86Updated last year
• yaojin17 / Unlearning_LLM
  [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
  ☆65Updated last year
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆79Updated last year
• jaechan-repo / muse_bench
  ☆30Updated last year
• sail-sg / closer-look-LLM-unlearning
  [ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models
  ☆41Updated last year
• ybwang119 / Awesome-reasoning-safety
  This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL
  ☆55Updated 3 months ago
• git-disl / Safety-Tax
  This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".
  ☆26Updated 9 months ago
• kevinyaobytedance / llm_unlearn
  LLM Unlearning
  ☆178Updated 2 years ago
• chujiezheng / LLM-Safeguard
  Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"
  ☆101Updated 7 months ago
• git-disl / Lisa
  This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)
  ☆25Updated last year
• yihuaihong / ConceptVectors
  [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆39Updated 4 months ago
• VITA-Group / SEAL
  [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free
  ☆47Updated 8 months ago
• javiferran / sae_entities
  ☆65Updated 9 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆98Updated last year
• vinid / safety-tuned-llamas
  ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.
  ☆90Updated last year
• vfleaking / PTST
  Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"
  ☆21Updated 3 months ago
• zjysteven / mink-plus-plus
  [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs
  ☆52Updated 6 months ago
• boyiwei / CoTaEval
  [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models
  ☆17Updated last year
• KID-22 / LLM-Unlearning-Paper-List
  ☆28Updated last week
• OPTML-Group / WAGLE
  Official repo for NeurIPS'24 paper "WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models"
  ☆16Updated last year
• CaoYuanpu / BiPO
  Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
  ☆38Updated last year