2 papers
cs.LG2026
Measuring all the noises of LLM Evals
Sida Wang
Separating signal from noise is central to experiments. Applying well-established statistical methods effectively to LLM evals requires consideration of their unique noise characte…
cs.CL2025
Structure-Aware Fill-in-the-Middle Pretraining for Code
Linyuan Gong, Alvin Cheung, Mostafa Elhoushi +1
Fill-in-the-Middle (FIM) is a common pretraining method for code LLMs, where models complete code segments given surrounding context. However, existing LLMs treat code as plain tex…