| Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models | Oct 25, 2024 | backdoor defenseModel Editing | CodeCode Available | 0 |
| Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models | Oct 13, 2024 | SST-2 | —Unverified | 0 |
| Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition | Jul 1, 2024 | Computational EfficiencySST-2 | —Unverified | 0 |
| SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN | Jun 5, 2024 | AllSST-2 | CodeCode Available | 1 |
| LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models | May 29, 2024 | Language ModellingSST-2 | —Unverified | 0 |
| Revisiting Character-level Adversarial Attacks for Language Models | May 7, 2024 | Adversarial AttackSentence | CodeCode Available | 1 |
| LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement | Mar 22, 2024 | Data AugmentationGSM8K | CodeCode Available | 2 |
| The Impact of Quantization on the Robustness of Transformer-based Text Classifiers | Mar 8, 2024 | QuantizationSST-2 | —Unverified | 0 |
| When does word order matter and when doesn't it? | Feb 29, 2024 | Natural Language UnderstandingRTE | CodeCode Available | 0 |
| Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge | Feb 29, 2024 | QNLISST-2 | CodeCode Available | 0 |
