metadata
license: mit
base_model: facebook/bart-large
tags:
- summarization
- scientific-text
- research-highlight-generation
- lora
language:
- en
RKMVNLP-scihigh-task1-bart-large-run1
BART-Large fine-tuned with LoRA for research highlight generation (FIRE SciHigh Subtask 1, MixSub-SciHigh). Team RKMV_NLP.
- Base model:
facebook/bart-large - Adapter: LoRA (r=16, alpha=32) on q/k/v/out_proj + fc1/fc2, merged into the base.
- Decoding: num_beams=6, length_penalty=0.8, no_repeat_ngram_size=3, min_length=45.
- Validation ROUGE-L F1 (decoding sweep best): ~0.248.
Input = paper abstract, output = research highlights.