| 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 |
| When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR) | Apr 1, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability | Mar 4, 2025 | GSM8KLogical Reasoning | CodeCode Available | 0 |
| Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models | Feb 20, 2025 | HellaSwagMemorization | —Unverified | 0 |
