Quality follows upgrading
Tag: cs.CL
arXiv:2604.00003v1 Announce Type: cross Abstract: This study evaluates the reliability of information extraction approaches from KRS documents using three strategies: LLM only, Hybrid Deterministic - …
arXiv:2604.01683v1 Announce Type: new Abstract: Standard scaled dot-product attention computes scores from static, independent projections of the input. We show that evolving queries and keys …
arXiv:2604.01476v1 Announce Type: new Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended …
arXiv:2604.00443v1 Announce Type: new Abstract: If the same neuron activates for both "lender" and "riverside," standard metrics attribute the overlap to superposition--the neuron must be …
arXiv:2604.00356v1 Announce Type: new Abstract: Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. …
arXiv:2604.00438v1 Announce Type: new Abstract: In-Context Reinforcement Learning (ICRL) enables Large Language Models (LLMs) to learn online from external rewards directly within the context window. …
arXiv:2604.00323v1 Announce Type: new Abstract: Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior. Traditional machine-learning approaches dependent on static …
arXiv:2604.00021v1 Announce Type: cross Abstract: Alignment safety research assumes that ethical instructions improve model behavior, but how language models internally process such instructions remains unknown. …
arXiv:2604.00024v1 Announce Type: new Abstract: Large language models are increasingly used for medical guidance, but women's health remains under-evaluated in benchmark design. We present the …
arXiv:2604.00890v1 Announce Type: new Abstract: Geometric Problem Solving (GPS) remains at the heart of enhancing mathematical reasoning in large language models because it requires the …
arXiv:2604.00477v1 Announce Type: new Abstract: LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their …
arXiv:2604.00025v1 Announce Type: new Abstract: Standard evaluation protocols reveal a counterintuitive phenomenon: on 7.7% of benchmark problems spanning five datasets, larger language models underperform smaller …
