peterljq / Parsimonious-Concept-Engineering
PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
☆35Updated 5 months ago
Alternatives and similar repositories for Parsimonious-Concept-Engineering:
Users that are interested in Parsimonious-Concept-Engineering are comparing it to the libraries listed below
- ☆13Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆70Updated 3 weeks ago
- Lightweight Adapting for Black-Box Large Language Models☆22Updated last year
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆26Updated 2 months ago
- ☆50Updated 2 weeks ago
- ☆23Updated 2 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆57Updated last year
- ☆27Updated last month
- Code for paper: Aligning Large Language Models with Representation Editing: A Control Perspective☆28Updated 2 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated last month
- ☆42Updated 2 months ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 2 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆77Updated 6 months ago
- Online Adaptation of Language Models with a Memory of Amortized Contexts (NeurIPS 2024)☆63Updated 8 months ago
- Codebase for Inference-Time Policy Adapters☆23Updated last year
- ☆41Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆84Updated 5 months ago
- Repo for: When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment☆38Updated last year
- General-purpose activation steering library☆61Updated 3 months ago
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆75Updated 4 months ago
- ☆33Updated 4 months ago
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated 5 months ago
- ☆31Updated 3 months ago
- ☆93Updated last year
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 2 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆73Updated last year
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆108Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆60Updated 3 months ago
- ☆37Updated last year
- ☆82Updated 8 months ago