arXiv:2505.12474v3 Announce Type: replace Abstract: Traditional dialogue summarization primarily focuses on dialogue content, assuming it comprises adequate information for a...

arXiv:2511.03410v1 Announce Type: new Abstract: Input errors in question-answering (QA) systems often lead to incorrect responses. Large language models (LLMs)...

arXiv:2508.00079v2 Announce Type: replace Abstract: The discipline of physics stands as a cornerstone of human intellect, driving the evolution of...

arXiv:2506.14562v3 Announce Type: replace Abstract: Weight decay is a standard regularization technique for training large language models (LLMs). While it...

arXiv:2502.18018v2 Announce Type: replace Abstract: The use of LLMs as automated judges (“LLM-as-a-judge”) is now widespread, yet standard judges suffer...

arXiv:2511.03542v1 Announce Type: new Abstract: Medical question answering systems face deployment challenges including hallucinations, bias, computational demands, privacy concerns, and...

arXiv:2511.02089v1 Announce Type: cross Abstract: Contrast-Consistent Search (CCS) is an unsupervised probing method able to test whether large language models...

arXiv:2511.02755v1 Announce Type: new Abstract: Large language models (LLMs) exhibit complementary strengths across domains and come with varying inference costs,...

arXiv:2511.02280v1 Announce Type: cross Abstract: We introduce SAIL-RL, a reinforcement learning (RL) post-training framework that enhances the reasoning capabilities of...