arXiv:2507.21108v1 Announce Type: new Abstract: Given the large size and volumes of contracts and their underlying inherent complexity, manual reviews...

arXiv:2507.07634v2 Announce Type: replace Abstract: We consider the problem of answering complex questions, given access to a large unstructured document...

arXiv:2507.21107v1 Announce Type: new Abstract: We propose Curved Inference – a geometric Interpretability framework that tracks how the residual stream...

Large language models (LLMs) have recently demonstrated remarkable progress in multi-step reasoning, establishing mathematical problem-solving as a rigorous benchmark for...

arXiv:2505.02820v2 Announce Type: replace-cross Abstract: Agents are predominantly evaluated and optimized via task success metrics, which are coarse, rely on...

arXiv:2507.19995v1 Announce Type: new Abstract: The advent of large language models (LLMs) has led to significant achievements in various domains,...

arXiv:2507.20924v1 Announce Type: new Abstract: Sexism has become widespread on social media and in online conversation. To help address this...

arXiv:2507.19980v1 Announce Type: new Abstract: This study investigates the estimation of reliability for large language models (LLMs) in scoring writing...