ahans30 / goldfish-loss
[NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs
☆84Updated 5 months ago
Alternatives and similar repositories for goldfish-loss:
Users that are interested in goldfish-loss are comparing it to the libraries listed below
- ☆23Updated 2 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆70Updated 3 weeks ago
- Exploration of automated dataset selection approaches at large scales.☆39Updated last month
- The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"☆108Updated last year
- Replicating O1 inference-time scaling laws☆83Updated 4 months ago
- The repository contains code for Adaptive Data Optimization☆23Updated 4 months ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆25Updated 5 months ago
- ☆31Updated 3 months ago
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆29Updated 3 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆45Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 5 months ago
- ☆174Updated last year
- ☆60Updated 11 months ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆77Updated 6 months ago
- ☆96Updated 9 months ago
- ☆27Updated 9 months ago
- Codebase for Instruction Following without Instruction Tuning☆34Updated 7 months ago
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆53Updated last year
- PyTorch library for Active Fine-Tuning☆64Updated 2 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆62Updated last year
- Exploring Model Kinship for Merging Large Language Models☆23Updated last week
- AI Logging for Interpretability and Explainability🔬☆111Updated 10 months ago
- An official implementation of "Catastrophic Failure of LLM Unlearning via Quantization" (ICLR 2025)☆26Updated 2 months ago
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆84Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆55Updated 7 months ago
- ☆47Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆69Updated 10 months ago
- [COLING'25] Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?☆72Updated 3 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆73Updated 4 months ago
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆49Updated 11 months ago