fc2869 / lo-fit
LoFiT: Localized Fine-tuning on LLM Representations
☆34Updated 2 months ago
Alternatives and similar repositories for lo-fit:
Users that are interested in lo-fit are comparing it to the libraries listed below
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆52Updated 3 months ago
- ☆30Updated 10 months ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆29Updated 4 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆69Updated 2 weeks ago
- ☆93Updated last year
- General-purpose activation steering library☆52Updated 2 months ago
- ☆47Updated last year
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆56Updated 11 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆107Updated 11 months ago
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆66Updated 2 years ago
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆60Updated last year
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆24Updated 3 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆131Updated 10 months ago
- Official PyTorch Implementation of EMoE: Unlocking Emergent Modularity in Large Language Models [main conference @ NAACL2024]☆29Updated 9 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆71Updated last year
- 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 last month
- Evaluating the Ripple Effects of Knowledge Editing in Language Models☆54Updated 11 months ago
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆73Updated 3 months ago
- AI Logging for Interpretability and Explainability🔬☆108Updated 9 months ago
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆107Updated 6 months ago
- AbstainQA, ACL 2024☆25Updated 5 months ago
- [ICLR'24 Spotlight] "Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts"☆67Updated 11 months ago
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs☆36Updated last month
- FeatureAlignment = Alignment + Mechanistic Interpretability☆28Updated 2 weeks ago
- ☆21Updated 6 months ago
- ☆47Updated 7 months ago
- [NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evalua…☆32Updated last year
- ☆16Updated 2 weeks ago
- ☆68Updated 3 months ago
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)☆58Updated last year