…Applying MedSP1000 to a range of general-purpose and medically specialized LLMs, we find that performance on static benchmarks does not reliably translate to such educational scenarios. The best-performing model, GPT…
…We propose CapCode, a framework for constructing coding datasets with randomized tests whose best achievable non-cheating performance is deliberately capped below one. This capped-performance design gives evaluation scores a clearer…
…While recent approaches treat NER and RE as separate tasks requiring distinct models, we introduce GLiNER -Relex, a unified architecture that extends the GLiNER framework to perform both entity recognition and relation…
…Tong Ye , , , , , , , , Abstract DOMINO enables domain-specific data synthesis through an inductive approach that learns domain representations from reference examples, improving code benchmark performance without requiring explicit domain descriptions. Generated by Qwen…
…Rian Touchent , Abstract Switching from Masked Language Modeling to Causal Language Modeling during encoder adaptation improves downstream performance on biomedical texts through dense supervision effects in lower transformer layers. AI-generated summary…
…Xingyu Qu , , Abstract Optimizer mismatch between Adam and Muon during fine-tuning degrades performance due to differing implicit biases, but this can be mitigated using parameter-efficient fine-tuning methods like LoRA…
…AI-generated summary Recent progress in reasoning models has substantially advanced long-horizon mathematical and scientific problem solving , with several systems now reaching gold-medal-level performance on International Mathematical Olympiad (IMO…
…Drawing inspiration from machine learning compilers , we introduce FlowCompile, a structured LLM workflow compiler that performs compile-time design space exploration to identify a high-quality, reusable trade-off set. FlowCompile decomposes…
…frontier large language models (LLMs), typically hosted in the cloud and offering strong performance across a wide range of tasks at substantially high cost, and more cost-efficient small language models (SLMs…
…Experiments show that AgentRunbook-C achieves the best performance with 72.5% average accuracy, outperforming the strongest RAG baseline (48.5%) and the off-the-shelf coding agent baseline (69.3%). Despite…