| Unsupervised Elicitation of Language Models | Jun 11, 2025 | GSM8KTruthfulQA | CodeCode Available | 0 |
| Model Unlearning via Sparse Autoencoder Subspace Guided Projections | May 30, 2025 | Adversarial Robustnessfeature selection | —Unverified | 0 |
| Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs | May 22, 2025 | HallucinationTruthfulQA | —Unverified | 0 |
| Truth Neurons | May 18, 2025 | TruthfulQA | CodeCode Available | 0 |
| Elastic Weight Consolidation for Full-Parameter Continual Pre-Training of Gemma2 | May 9, 2025 | ARCBelebele | —Unverified | 0 |
| DYNAMAX: Dynamic computing for Transformers and Mamba based architectures | Apr 29, 2025 | MambaTriviaQA | —Unverified | 0 |
| Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer | Apr 17, 2025 | Conformal PredictionTruthfulQA | —Unverified | 0 |
| Sample, Don't Search: Rethinking Test-Time Alignment for Language Models | Apr 4, 2025 | GSM8KMathematical Reasoning | —Unverified | 0 |
| Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency | Apr 4, 2025 | BenchmarkingGSM8K | —Unverified | 0 |
| More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment | Apr 3, 2025 | ARCHellaSwag | —Unverified | 0 |