| PARAMANU-AYN: Pretrain from scratch or Continual Pretraining of LLMs for Legal Domain Adaptation? | Mar 20, 2024 | Abstractive Text SummarizationContinual Pretraining | —Unverified | 0 |
| Instructing Large Language Models to Identify and Ignore Irrelevant Conditions | Mar 19, 2024 | MathMathematical Reasoning | CodeCode Available | 0 |
| An upper bound of the mutation probability in the genetic algorithm for general 0-1 knapsack problem | Mar 17, 2024 | DiversityEvolutionary Algorithms | —Unverified | 0 |
| What Makes Math Word Problems Challenging for LLMs? | Mar 17, 2024 | Math | CodeCode Available | 0 |
| Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning | Mar 14, 2024 | Deep Reinforcement LearningGraph Attention | CodeCode Available | 0 |
| Sabiá-2: A New Generation of Portuguese Large Language Models | Mar 14, 2024 | Math | —Unverified | 0 |
| Hydrodynamics of Markets:Hidden Links Between Physics and Finance | Mar 14, 2024 | Math | —Unverified | 0 |
| Laying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks | Mar 14, 2024 | MathSkill Generalization | —Unverified | 0 |
| Self-Consistency Boosts Calibration for Math Reasoning | Mar 14, 2024 | GSM8KMath | —Unverified | 0 |
| Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models | Mar 13, 2024 | Math | —Unverified | 0 |
