UQ4CT integrates functional-level uncertainty calibration into mixture-of-experts LoRA fine-tuning via a dedicated loss, cutting expected calibration error by over 25% on multiple-choice and generative QA tasks.
Benchmarking llms via uncertainty quantification.arXiv preprint arXiv:2401.12794
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Reasoning before answering MCQs increases LLM confidence more for incorrect answers and degrades calibration on a 57-subject benchmark across seven models.
citing papers explorer
-
Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs
UQ4CT integrates functional-level uncertainty calibration into mixture-of-experts LoRA fine-tuning via a dedicated loss, cutting expected calibration error by over 25% on multiple-choice and generative QA tasks.
-
Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong
Reasoning before answering MCQs increases LLM confidence more for incorrect answers and degrades calibration on a 57-subject benchmark across seven models.