QNLI

anchor

Findings

• IC-327Llama-3-8B-Instruct, Mistral-7B-Instruct-v0.3, and several other LLMs produce well-calibrated verbal confidence estimates on classification tasks [eval]
• IC-746RoBERTa-Large pretrained with different mask ratios exhibits a sweet spot in downstream accuracy on QNLI and SST-2 [eval]