Update README.md

README.md

@@ -73,12 +73,9 @@ as evidenced by evaluation results on Singapore's [Multitask National Speech Cor
 > MNSC is a multitask speech understanding dataset derived and further annotated from [IMDA NSC Corpus](https://www.imda.gov.sg/how-we-can-help/national-speech-corpus).
 > It focuses on the knowledge of Singapore's local accent, localised terms, and code-switching.
 
-> [!NOTE]
-> We assess ASR and ST tasks using Word Error Rate (WER) and BLEU scores, respectively.
-> For other tasks, we employ the LLM-as-a-Judge framework,
-> which uses a pre-trained large language model to evaluate task performance
-> by generating and scoring responses based on relevance, coherence, and accuracy criteria.
-> Refer to the [AudioBench paper](https://arxiv.org/abs/2406.16020) for more details.
+We assess ASR and ST tasks using Word Error Rate (WER) and BLEU scores, respectively. For other tasks, we employ the LLM-as-a-Judge framework,
+which uses a pre-trained large language model to evaluate task performance by generating and scoring responses based on relevance, coherence, and accuracy criteria.
+Refer to the [AudioBench paper](https://arxiv.org/abs/2406.16020) for more details.
 
 <div class="table*">
 <table>
@@ -568,12 +565,16 @@ With a global batch size of 640, we train the current release of MERaLiON-AudioL
 
 ## Citation
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
+If you find our work useful, please cite our paper:
 
-**APA:**
-
-[More Information Needed]
+```
+@misc{he2024meralionaudiollmtechnicalreport,
+      title={MERaLiON-AudioLLM: Technical Report}, 
+      author={Yingxu He and Zhuohan Liu and Shuo Sun and Bin Wang and Wenyu Zhang and Xunlong Zou and Nancy F. Chen and Ai Ti Aw},
+      year={2024},
+      eprint={2412.09818},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2412.09818}, 
+}
+```