Fine-tuning a Gemma model on a mix of seed, generated, and general instruction data (ArgInstruct) improves zero-shot performance on unseen computational argumentation tasks while preserving general NLP performance.
Title resolution pending
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation
Fine-tuning a Gemma model on a mix of seed, generated, and general instruction data (ArgInstruct) improves zero-shot performance on unseen computational argumentation tasks while preserving general NLP performance.