Update README.md

README.md

@@ -16,6 +16,7 @@ datasets:
 - microsoft/NextCoderDataset
 - microsoft/NextCoderDataset-Conversational
 - bigcode/commitpackft
+- bigcode/starcoderdata
 ---
 
 
@@ -119,7 +120,7 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 
 *Comparison of base QwenCoder-2.5 models of different sizes and their SELEKT-enhanced versions across three code editing benchmarks.*
 
-**Detailed evaluation results are reported in this [📑 paper](https://arxiv.org/abs/2503.03656).**
+**Detailed evaluation results are reported in this [📑 paper](https://www.microsoft.com/en-us/research/publication/nextcoder-robust-adaptation-of-code-lms-to-diverse-code-edits/).**
 
 ## Responsible AI Use
 The base models (from the QwenCoder-2.5 family) are suspectible to malicious prompts and may generate or execute harmful code. Our finetuning does not enhance or impede such behaviors. The users should use the models and their outputs responsibly and with caution. Model outputs should be subjected to additional analysis, including manual inspection, and sandboxing before execution.