Alternatives and similar repositories for safety-arithmetic

Users that are interested in safety-arithmetic are comparing it to the libraries listed below

• VITA-Group / SEAL
  [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free
  ☆51Updated 10 months ago
• alisawuffles / proxy-tuning
  Code associated with Tuning Language Models by Proxy (Liu et al., 2024)
  ☆127Updated last year
• princeton-nlp / benign-data-breaks-safety
  ☆44Updated last year
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆98Updated last year
• hkust-nlp / Activation_Decoding
  In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)
  ☆62Updated last year
• yihuaihong / ConceptVectors
  [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆39Updated 5 months ago
• yuzhaouoe / SAE-based-representation-engineering
  [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
  ☆72Updated 3 weeks ago
• ChenmienTan / malmen
  ☆37Updated 2 years ago
• pillowsofwind / Course-Correction
  [EMNLP 2024] The official GitHub repo for the paper "Course-Correction: Safety Alignment Using Synthetic Preferences"
  ☆20Updated last year
• boyiwei / alignment-attribution-code
  [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
  ☆89Updated 10 months ago
• CaoYuanpu / BiPO
  Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
  ☆41Updated last year
• yaojin17 / Unlearning_LLM
  [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
  ☆66Updated last year
• boyiwei / CoTaEval
  [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models
  ☆17Updated last year
• WANGXinyiLinda / planning_tokens
  Official code for Guiding Language Model Math Reasoning with Planning Tokens
  ☆18Updated last year
• zepingyu0512 / neuron-attribution
  code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models
  ☆50Updated last year
• licong-lin / negative-preference-optimization
  ☆72Updated last year
• fc2869 / lo-fit
  LoFiT: Localized Fine-tuning on LLM Representations
  ☆44Updated last year
• XuandongZhao / weak-to-strong
  [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models
  ☆92Updated 9 months ago
• MikaStars39 / FeatureAlignment
  FeatureAlignment = Alignment + Mechanistic Interpretability
  ☆34Updated 11 months ago
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆80Updated last year
• thu-coai / SafeUnlearning
  Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
  ☆32Updated last year
• git-disl / Vaccine
  This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)
  ☆49Updated 3 weeks ago
• javiferran / sae_entities
  ☆69Updated 11 months ago
• deeplearning-wisc / picle
  Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)
  ☆26Updated last year
• TaiMingLu / know-dont-tell
  ☆19Updated last year
• DYR1 / MoGU
  Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.
  ☆18Updated last year
• HillZhang1999 / ICD
  Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"
  ☆69Updated last year
• hahahawu / Long-to-Short-via-Model-Merging
  Model merging is a highly efficient approach for long-to-short reasoning.
  ☆98Updated 3 months ago
• zjysteven / mink-plus-plus
  [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs
  ☆52Updated 8 months ago
• jinzhuoran / RWKU
  RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024
  ☆89Updated last year