4 papers
Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage
Eric Fithian, Kirill Skobelev, X. Y. Han
In verifiable domains such as math and coding, finding one correct solution among many attempts can matter more than the pass rate of each attempt. Post-training can concentrate la…
Fine-Tuning Fixes Mode Collapse and Over-Dispersion in LLMs
Kirill Skobelev, Eric Fithian, X. Y. Han
Recent work by Doshi and Hauser (2024), Bisbee et al. (2024), and Xie et al. (2026) raises concerns that outputs from large language models (LLMs) tend to be under-diverse: they re…
A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling
Kirill Skobelev, Eric Fithian, Yegor Baranovski +9
Recent Artificial Intelligence (AI) models have matched or exceeded human experts in several benchmarks of biomedical task performance, but surgical benchmarks in particular are of…
DELM: a Python toolkit for Data Extraction with Language Models
Eric Fithian, Kirill Skobelev
Large Language Models (LLMs) have become powerful tools for annotating unstructured data. However, most existing workflows rely on ad hoc scripts, making reproducibility, robustnes…