Qwen3-4B-OutsideTheBox-SFT
This repository provides the supervised fine-tuning checkpoint developed for the paper Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?
Model Description
The model is initialized from Qwen3-4B and fine-tuned on workflow-conditioned mathematical reasoning data. The training examples pair problems with external workflows of varying quality so that the model can learn to use helpful guidance while handling misleading guidance.
Intended Use
This checkpoint is intended for research on mathematical reasoning, external workflow utilization, and robustness to incorrect guidance. It corresponds to the SFT stage reported in the paper.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "ElvisWang111/Qwen3-4B-OutsideTheBox-SFT"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype="auto",
device_map="auto",
)
Base Model
- Base model:
Qwen/Qwen3-4B - Training stage: supervised fine-tuning (SFT)
- Domain: workflow-conditioned mathematical reasoning