Tag: cs.CL
arXiv:2602.21227v1 Announce Type: cross Abstract: As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step …
arXiv:2602.21228v1 Announce Type: cross Abstract: As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing …
arXiv:2602.21231v1 Announce Type: cross Abstract: We present ACAR (Adaptive Complexity and Attribution Routing), a measurement framework for studying multi-model orchestration under auditable conditions. ACAR uses …
arXiv:2602.21346v1 Announce Type: cross Abstract: Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization …
arXiv:2602.21368v1 Announce Type: cross Abstract: Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We …
arXiv:2602.21374v1 Announce Type: cross Abstract: Extracting clinical information from medical transcripts in low-resource languages remains a significant challenge in healthcare natural language processing (NLP). This …
arXiv:2602.21379v1 Announce Type: cross Abstract: We introduce MrBERT, a family of 150M-300M parameter encoders built on the ModernBERT architecture and pre-trained on 35 languages and …
arXiv:2602.22215v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate potential in the field of scientific idea generation. However, the generated results often lack controllable …
arXiv:2602.22441v1 Announce Type: new Abstract: Latent reasoning has been recently proposed as a reasoning paradigm and performs multi-step reasoning through generating steps in the latent …
arXiv:2602.22480v1 Announce Type: new Abstract: An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles. …
arXiv:2602.22523v1 Announce Type: new Abstract: While contemporary large language models (LLMs) are increasingly capable in isolation, there are still many difficult problems that lie beyond …
arXiv:2602.22583v1 Announce Type: new Abstract: Example-based guidance is widely used to improve mathematical reasoning at inference time, yet its effectiveness is highly unstable across problems …
