Update README.md

README.md

@@ -28,7 +28,7 @@ pipeline_tag: text-generation
 
 ### Model Sources 
 
-- **Paper:** [COMING SOON]  
+- **Paper:** Rethinking Low-Resource MT: The Surprising Effectiveness of Fine-Tuned Multilingual Models in the LLM Age (Scalvini et al., NoDaLiDa 2025)
 ---
 
 ## Uses
@@ -110,7 +110,7 @@ for sentence in sentences:
 
     # Generate the output
     outputs = model.generate(**inputs,
-                             max_new_tokens=2000, 
+                             max_new_tokens=500, 
                              eos_token_id=tokenizer.eos_token_id,  # Ensure EOS token is used
                              pad_token_id=tokenizer.pad_token_id,  # Ensure padding token is used
                              use_cache=True,
@@ -144,8 +144,7 @@ for sentence in sentences:
 
 ### Training Data
 
-We used the Sprotin parallel corpus for **English–Faroese** translation: [barbaroo/Sprotin_parallel](https://huggingface.co/datasets/barbaroo/Sprotin_parallel). 
-
+We used the Sprotin parallel corpus for **English–Faroese** translation: [barbaroo/Sprotin_parallel](https://huggingface.co/datasets/barbaroo/Sprotin_parallel).
 
 ### Training Procedure
 
@@ -182,8 +181,8 @@ Human evaluation was also performed (see paper)
 
 
 ## Citation []
+Barbara Scalvini, Iben Nyholm Debess, Annika Simonsen, and Hafsteinn Einarsson. 2025. Rethinking Low-Resource MT: The Surprising Effectiveness of Fine-Tuned Multilingual Models in the LLM Age. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), pages 609–621, Tallinn, Estonia. University of Tartu Library.
 
-[COMING SOON]
 
 ---
 ## Framework versions