ahans30 / goldfish-loss
[NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs
☆84Updated 4 months ago
Alternatives and similar repositories for goldfish-loss:
Users that are interested in goldfish-loss are comparing it to the libraries listed below
- ☆22Updated last month
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆62Updated this week
- The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"☆108Updated last year
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆29Updated 2 months ago
- ☆96Updated 9 months ago
- Implementation of PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 4 months ago
- ☆31Updated 2 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆73Updated 4 months ago
- The repository contains code for Adaptive Data Optimization☆20Updated 3 months ago
- ☆60Updated 11 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆61Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆67Updated 9 months ago
- ☆26Updated 8 months ago
- PyTorch library for Active Fine-Tuning☆62Updated last month
- Exploration of automated dataset selection approaches at large scales.☆34Updated 3 weeks ago
- Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]☆66Updated 2 months ago
- ☆172Updated last year
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆33Updated last month
- Knowledge Unlearning for Large Language Models☆22Updated 3 weeks ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆42Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆28Updated last week
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆82Updated last year
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆67Updated last year
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆24Updated 4 months ago
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆26Updated last month
- Long Context Extension and Generalization in LLMs☆50Updated 6 months ago
- Replicating O1 inference-time scaling laws☆83Updated 4 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
- ☆53Updated 2 years ago
- AI Logging for Interpretability and Explainability🔬☆110Updated 9 months ago