Alternatives and similar repositories for emulated-disalignment:

Users that are interested in emulated-disalignment are comparing it to the libraries listed below

• ZHZisZZ / modpo
  [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
  ☆76Updated 8 months ago
• boyiwei / alignment-attribution-code
  [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆76Updated last month
• srzer / MOD
  Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".
  ☆22Updated 6 months ago
• alexrame / rewardedsoups
  Rewarded soups official implementation
  ☆57Updated last year
• zhxieml / remiss-jailbreak
  ☆28Updated 10 months ago
• deeplearning-wisc / args
  ☆40Updated last year
• Unispac / shallow-vs-deep-alignment
  Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep
  ☆110Updated 2 weeks ago
• YangRui2015 / Generalizable-Reward-Model
  Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"
  ☆33Updated 2 months ago
• YangRui2015 / RiC
  Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"
  ☆68Updated 4 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆72Updated 2 months ago
• princeton-nlp / benign-data-breaks-safety
  ☆36Updated 7 months ago
• limenlp / verl
  AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
  ☆29Updated 3 weeks ago
• Jiacheng-Zhu-AIML / AsymmetryLoRA
  Preprint: Asymmetry in Low-Rank Adapters of Foundation Models
  ☆36Updated last year
• uw-nsl / safechain
  SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
  ☆13Updated last month
• ChnQ / TracingLLM
  ☆25Updated 11 months ago
• Zhou-Zoey / RMB-Reward-Model-Benchmark
  ☆35Updated last month
• Improbable-AI / curiosity_redteam
  Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…
  ☆75Updated last year
• dannyallover / overthinking_the_truth
  ☆29Updated last year
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆92Updated 11 months ago
• abhishekpanigrahi1996 / Skill-Localization-by-grafting
  ☆49Updated last year
• RLHFlow / Directional-Preference-Alignment
  Directional Preference Alignment
  ☆57Updated 7 months ago
• yaojin17 / Unlearning_LLM
  [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
  ☆58Updated 7 months ago
• ADaM-BJTU / W2SG
  The code of “Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning”
  ☆16Updated last year
• keven980716 / weak-to-strong-deception
  [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"
  ☆13Updated 10 months ago
• VITA-Group / SEAL
  Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free
  ☆20Updated last month
• vfleaking / PTST
  Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"
  ☆18Updated last year
• git-disl / Safety-Tax
  This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".
  ☆15Updated last month
• hahahawu / Long-to-Short-via-Model-Merging
  Model merging is a highly efficient approach for long-to-short reasoning.
  ☆43Updated last month
• sanowl / Self-Correcting-LLM--Reinforcement-Learning-
  This my attempt to create Self-Correcting-LLM based on the paper Training Language Models to Self-Correct via Reinforcement Learning by g…
  ☆35Updated last month
• git-disl / Vaccine
  This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
  ☆42Updated 5 months ago