CLSGen is a dual-head LLM fine-tuning framework that enables joint probabilistic classification and verbalized explanation generation without catastrophic forgetting of generative capabilities.
Using tournaments to calculate auroc for zero-shot classification with llms.arXiv preprint arXiv:2502.15018, 2025a
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CLSGen: A Dual-Head Fine-Tuning Framework for Joint Probabilistic Classification and Verbalized Explanation
CLSGen is a dual-head LLM fine-tuning framework that enables joint probabilistic classification and verbalized explanation generation without catastrophic forgetting of generative capabilities.