|
--- |
|
license: apache-2.0 |
|
--- |
|
|
|
This is the LACIE fine-tuned version of Llama-3 70B, finetuned according to our paper [LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models](arxiv.org/abs/2405.21028) |
|
|
|
This model is a fine-tuned version of [Llama-3 70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B) that has been finetuned using data from [TriviaQA](https://huggingface.co/datasets/mandarjoshi/trivia_qa). |
|
LACIE is pragmatic preference-based finetuning method that optimizes models to be better calibrated w.r.t. both implicit and explicit confidence statements. |
|
The preferences in the dataset are based on correctness and whether listener accepted to rejected the answer. |
|
For more details, please see our paper. |
|
|
|
## Model Architecture |
|
The architecture is the same as Llama-3 70B; the weights in this repo are adapter weights for Llama. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
