general family · filed under post-training
Supervised fine-tuning
Supervised post-training used to establish or improve a model's behavior; the evidence does not specify one particular data or training recipe.
Also called SFT, Supervised Fine Tuning (SFT).
- sources
- 14
- models
- 7
- labs adopt it
- 5
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
Documented in
Further reading
Picked by hand, not extracted: where to read more, not evidence for anything on this page.
- Finetuned Language Models Are Zero-Shot Learners (Wei et al., 2021) paper arxiv.orgcanonical instruction-tuning / SFT reference
Evidence
17 spans quoted from the sources, strongest treatment first.
Through joint optimization of SFT and RL
The SFT stage establishes a high-quality cold-start policy for the subsequent RL stage.
Through joint optimization of SFT and RL
post-trained using Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation
To train the student model, we start from the pre-trained base model and perform Supervised Fine-Tuning (SFT) in two stages
Supervised Fine-Tuning (SFT) to build strong, foundational instruction-following skills
Post-trained with enhanced pipeline involving Supervised Fine Tuning (SFT), Reinforcement Learning (RL), and Multi-teacher On-Policy Distillation (MOPD) for improved model accuracy.
each specialist goes through its own Supervised Fine-Tuning (SFT) on domain-specific data
The model was further fine-tuned on synthetic code, math, science, tool calling, instruction following, structured outputs, and general knowledge data.
Post-training incorporates SFT, large-scale agentic RL, and Multi-Teacher On-Policy Distillation (MOPD)
Supervised Fine-Tuning (SFT) in two stages
To improve upon SFT model, we conduct a unified RLVR
post-trained using SFT, RL, and MOPD
independent cultivation of domain-specific experts (through SFT and RL with GRPO)
Post-training incorporates SFT, large-scale agentic RL, and Multi-Teacher On-Policy Distillation (MOPD)
general Supervised Fine-Tuning (SFT)
supervised fine-tuning and agentic post-training
Filed alongside
Other methods under post-training :: supervised fine-tuning.