yihuaihong / ConceptVectorsLinks
ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"
☆35Updated 3 months ago
Alternatives and similar repositories for ConceptVectors
Users that are interested in ConceptVectors are comparing it to the libraries listed below
Sorting:
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated last week
- ☆44Updated last year
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆34Updated 6 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 4 months ago
- [ACL 2024 main] Aligning Large Language Models with Human Preferences through Representation Engineering (https://aclanthology.org/2024.…☆24Updated 8 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆59Updated last year
- ☆36Updated 2 months ago
- ☆34Updated 2 weeks ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆57Updated 8 months ago
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs☆37Updated last week
- ☆41Updated 8 months ago
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated 10 months ago
- ☆44Updated 3 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆58Updated 6 months ago
- ☆29Updated last year
- LoFiT: Localized Fine-tuning on LLM Representations☆39Updated 4 months ago
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆68Updated 2 years ago
- ☆23Updated 9 months ago
- Code for "Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective"☆31Updated last year
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆27Updated 3 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 7 months ago
- ☆58Updated 10 months ago
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆15Updated 4 months ago
- ☆37Updated last year
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆30Updated 4 months ago
- [NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evalua…☆33Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 2 months ago
- General-purpose activation steering library☆74Updated 3 weeks ago
- Official code implementation of SKU, Accepted by ACL 2024 Findings☆15Updated 5 months ago