Update README.md

README.md

@@ -19,5 +19,30 @@ widget:
 
 # Model Card for long-t5-tglobal-large-AERA
 
-This repository provides a fine-tuned version of long-t5-tglobal-large, using our proposed [AERA](https://github.com/lijiazheng99/aera/tree/main) framework presented in the paper: [Distilling ChatGPT for Explainable Automated Student Answer Assessment](https://aclanthology.org/2023.findings-emnlp.399.pdf).
+This repository provides a fine-tuned version of long-t5-tglobal-large, using our proposed [AERA](https://github.com/lijiazheng99/aera/tree/main) framework presented in the paper: [Distilling ChatGPT for Explainable Automated Student Answer Assessment](https://aclanthology.org/2023.findings-emnlp.399.pdf). 
 
+## Citation Information
+
+```bibtex
+@inproceedings{li-etal-2023-distilling,
+    title = "Distilling {C}hat{GPT} for Explainable Automated Student Answer Assessment",
+    author = "Li, Jiazheng  and
+      Gui, Lin  and
+      Zhou, Yuxiang  and
+      West, David  and
+      Aloisi, Cesare  and
+      He, Yulan",
+    editor = "Bouamor, Houda  and
+      Pino, Juan  and
+      Bali, Kalika",
+    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
+    month = dec,
+    year = "2023",
+    address = "Singapore",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2023.findings-emnlp.399",
+    doi = "10.18653/v1/2023.findings-emnlp.399",
+    pages = "6007--6026",
+    abstract = "Providing explainable and faithful feedback is crucial for automated student answer assessment. In this paper, we introduce a novel framework that explores using ChatGPT, a cutting-edge large language model, for the concurrent tasks of student answer scoring and rationale generation. We identify the appropriate instructions by prompting ChatGPT with different templates to collect the rationales, where inconsistent rationales are refined to align with marking standards. The refined ChatGPT outputs enable us to fine-tune a smaller language model that simultaneously assesses student answers and provides rationales. Extensive experiments on the benchmark dataset show that the proposed method improves the overall QWK score by 11{\%} compared to ChatGPT. Furthermore, our thorough analysis and human evaluation demonstrate that the rationales generated by our proposed method are comparable to those of ChatGPT. Our approach provides a viable solution to achieve explainable automated assessment in education",
+}
+```