peterljq / Parsimonious-Concept-Engineering

Related projects: ⓘ

• haotiansun14 / BBox-Adapter
  Lightweight Adapting for Black-Box Large Language Models
  ☆16Updated 7 months ago
• Vaidehi99 / InfoDeletionAttacks
  ☆37Updated 10 months ago
• yaojin17 / Unlearning_LLM
  [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
  ☆34Updated 4 months ago
• nik-dim / tall_masks
  Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
  ☆26Updated 3 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆46Updated last month
• ejones313 / auditing-llms
  ☆47Updated last year
• tatsu-lab / test_set_contamination
  ☆32Updated 10 months ago
• JasonForJoy / Model-Editing-Hurt
  Model Editing Can Hurt General Abilities of Large Language Models
  ☆29Updated 7 months ago
• hkust-nlp / Activation_Decoding
  ☆40Updated 5 months ago
• Thartvigsen / GRACE
  [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
  ☆64Updated 6 months ago
• chrisliu298 / awesome-representation-engineering
  A resource repository for representation engineering in large language models
  ☆35Updated last week
• yihuaihong / ConceptVectors
  ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
  ☆14Updated 2 weeks ago
• zjunlp / KnowledgeCircuits
  Knowledge Circuits in Pretrained Transformers
  ☆45Updated 2 weeks ago
• ykwon0407 / DataInf
  DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)
  ☆46Updated 5 months ago
• centerforaisafety / wmdp
  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…
  ☆71Updated 4 months ago
• ADaM-BJTU / W2SG
  The code of “Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning”
  ☆15Updated 6 months ago
• SafeAILab / RAIN
  [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning
  ☆79Updated 3 months ago
• alisawuffles / proxy-tuning
  Code associated with Tuning Language Models by Proxy (Liu et al., 2024)
  ☆84Updated 5 months ago
• adymaharana / d2pruning
  ☆25Updated 11 months ago
• UCSB-NLP-Chang / llm_uncertainty
  ☆21Updated 7 months ago
• XuandongZhao / weak-to-strong
  Weak-to-Strong Jailbreaking on Large Language Models
  ☆62Updated 6 months ago
• locuslab / tofu
  Landing Page for TOFU
  ☆79Updated 3 months ago
• zjunlp / PitfallsKnowledgeEditing
  [ICLR 2024] Unveiling the Pitfalls of Knowledge Editing for Large Language Models
  ☆22Updated 3 months ago
• activatedgeek / calibration-tuning
  ☆30Updated last month
• dannyallover / overthinking_the_truth
  ☆24Updated 4 months ago
• chujiezheng / LLM-Safeguard
  Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"
  ☆64Updated 2 weeks ago
• roeehendel / icl_task_vectors
  ☆68Updated 10 months ago
• locuslab / acr-memorization
  ☆23Updated 4 months ago
• abhishekpanigrahi1996 / Skill-Localization-by-grafting
  ☆38Updated 8 months ago
• zhaoyiran924 / Probe-Sampling
  Code of paper "Accelerating Greedy Coordinate Gradient via Probe Sampling"
  ☆16Updated 5 months ago