peterljq / Parsimonious-Concept-Engineering
Implementation of PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)
☆35Updated 4 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
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆62Updated this week
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆75Updated 5 months ago
- ☆17Updated 3 weeks ago
- ☆31Updated last year
- ☆30Updated 3 months ago
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆33Updated last month
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆29Updated 2 months ago
- ☆49Updated 7 months ago
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆26Updated last month
- 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
- ☆13Updated last year
- ☆29Updated 11 months ago
- ☆27Updated last month
- ☆53Updated 2 years ago
- ☆42Updated last month
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated 4 months ago
- ☆22Updated last month
- ☆42Updated 2 years ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆71Updated 3 weeks ago
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆47Updated 3 weeks ago
- Knowledge Unlearning for Large Language Models☆22Updated 3 weeks ago
- ☆38Updated last year
- ☆37Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆89Updated 10 months ago
- ☆37Updated last year
- Lightweight Adapting for Black-Box Large Language Models☆22Updated last year
- ☆93Updated last year
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆56Updated 6 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆43Updated 8 months ago
- General-purpose activation steering library☆54Updated 2 months ago