Update README.md

README.md

@@ -22,7 +22,7 @@ This model is trained on the UltraFeedback dataset (using the per-aspect/fine-gr
 We used a 70B RM trained on the UltraFeedback dataset, and then used the UltraFeedback prompts during PPO training.
 
 For more details, read the paper:
-[Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://link.todo).
+[Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://arxiv.org/abs/2406.09279).
 
 
 ## .Model description
@@ -44,7 +44,7 @@ For more details, read the paper:
 
 Tulu V2.5 PPO is trained to be a generalist model, and matches or outperforms Tulu 2+DPO 13B.
 It even beats Tulu 2+DPO 70B in some cases, although it loses out in harder reasoning tasks.
-For details on training and evaluation, read [our paper](https://link.todo)!
+For details on training and evaluation, read [our paper](https://arxiv.org/abs/2406.09279)!
 
 
 | Model | Size | Alignment | GSM8k 8-shot CoT Acc. | AlpacaEval 2 Winrate (LC) | Average Perf. across Open-Instruct evals  |
@@ -125,6 +125,7 @@ If you find Tulu 2.5 is useful in your work, please cite it with:
       title={{Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback}}, 
       author={{Hamish Ivison and Yizhong Wang and Jiacheng Liu and Ellen Wu and Valentina Pyatkin and Nathan Lambert and Yejin Choi and Noah A. Smith and Hannaneh Hajishirzi}}
       year={2024},
+      eprint={2406.09279},
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }