hartvigsen-group / composable-interventionsLinks
☆28Updated 8 months ago
Alternatives and similar repositories for composable-interventions
Users that are interested in composable-interventions are comparing it to the libraries listed below
Sorting:
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 4 months ago
- Exploration of automated dataset selection approaches at large scales.☆48Updated 7 months ago
- ☆51Updated last year
- ☆33Updated 9 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆40Updated 11 months ago
- [ICLR 2025] Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization☆31Updated 9 months ago
- Code for "Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective"☆32Updated last year
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆31Updated 9 months ago
- ☆52Updated 6 months ago
- ☆16Updated last year
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆33Updated 8 months ago
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Updated 6 months ago
- ☆40Updated last year
- Confidence Regulation Neurons in Language Models (NeurIPS 2024)☆12Updated 8 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated 11 months ago
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 2 months ago
- Recycling diverse models☆46Updated 2 years ago
- PyTorch codes for the paper "An Empirical Study of Multimodal Model Merging"☆37Updated 2 years ago
- code for EMNLP 2024 paper: How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for M…☆13Updated 11 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆84Updated last year
- ☆46Updated 8 months ago
- Optimize Any User-defined Compound AI Systems☆59Updated 2 months ago
- ☆20Updated last year
- Few-shot Learning with Auxiliary Data☆31Updated last year
- Lightweight Adapting for Black-Box Large Language Models☆23Updated last year
- Test-time-training on nearest neighbors for large language models☆46Updated last year
- Trains Sparse Autoencoders based on outputs from language models☆11Updated last year
- ☆21Updated last month
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆37Updated 5 months ago
- ☆32Updated 9 months ago