🎯 Supervised fine-tuning

The items that name it 7

• From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe
  paper2026-10-28

  The training stage at which the flip in how a poster's job is interpreted happens in OLMo-2 32B.

• Locating Sycophancy Across Training Stages in Open Language Models
  paper2026-10-27

  A training stage between base model and release that the study measures for sycophancy.

• Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution
  paper2026-10-08It is written here as Supervised fine-tuning (SFT).

  SFT

• How to train your model organism
  paper2026-10-07It is written here as Supervised finetuning (SFT).

  SFT

• One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO
  article2026-10-07It is written here as Supervised fine-tuning (SFT).

  SFT

• A Systematic Study of Small Language Models on Abstract Reasoning Tasks
  paper2026-10-06
• Open-sourcing AstaBrief, the fast report-generation model in Asta
  article2026-10-02It is written here as Supervised fine-tuning (SFT).

  SFT

In every workspace you can read 8