Update README.md

README.md

@@ -29,7 +29,7 @@ This is one of 3 identical versions trained with different random seeds.
 - **Language(s)**: English
 - **License**: Apache 2.0
 - **Finetuned from**: `google/t5-v1_1-xxl`
-- **Paper**: https://arxiv.org/abs/2507.XXXXX
+- **Paper**: https://arxiv.org/abs/2507.07186
 - **Repository**: https://github.com/itay1itzhak/planted-in-pretraining
 
 ## Uses
@@ -77,4 +77,18 @@ print(tokenizer.decode(outputs[0]))
 ## Technical Specifications
 
 - Architecture: T5-11B
-- Instruction dataset: Tulu-2
+- Instruction dataset: Tulu-2
+
+## Citation
+
+```bibtex
+@misc{itzhak2025plantedpretrainingswayedfinetuning,
+      title={Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs}, 
+      author={Itay Itzhak and Yonatan Belinkov and Gabriel Stanovsky},
+      year={2025},
+      eprint={2507.07186},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2507.07186}, 
+}
+```