Update README.md

README.md

@@ -42,12 +42,12 @@ This paradigm begins with supervised fine-tuning on samples with weak audio cont
 
 Our model loading and usage methods are identical to those of Qwen2.5-Omni. Please refer to the [official documentation](https://github.com/QwenLM/Qwen2.5-Omni).
 
-### Input Format
+### Input Format (Updated on 2026-03-08)
 
 The evaluation input prompt structure is:
 
 ```
-[Question] Please choose the answer from the following options: ["Option1", "Option2", "Option3", "Option4"]. Output the final answer in <answer> </answer>.
+[Question] Please choose the answer from the following options: ['Option1', 'Option2', 'Option3', 'Option4']. Output the final answer in <answer> </answer>.
 ```
 
 ### Example Usage
@@ -81,11 +81,11 @@ For detailed performance metrics and comparisons, please refer to our paper.
 If you find this model useful in your research, please cite:
 
 ```bibtex
-@article{he2025audiomcq,
+@inproceedings{he2025audiomcq,
   title={Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models},
   author={He, Haolin and others},
-  journal={arXiv preprint arXiv:2509.21060},
-  year={2025}
+  booktitle={Proceedings of the International Conference on Learning Representations (ICLR)},
+  year={2026}
 }
 ```