In this work, we study the alignment (BrainScore) of large language models (LLMs) fine-tuned for moral reasoning on behavioral data and/or brain data of humans performing the same task. We also explore if fine-tuning several LLMs on the fMRI data of humans performing moral reasoning can improve the BrainScore. We fine-tune several LLMs (BERT, RoBERTa, DeBERTa) on moral reasoning behavioral data from the ETHICS benchmark [Hendrycks et al., 2020], on the moral reasoning fMRI data from Koster-Hale et al. [2013], or on both. We study both the accuracy on the ETHICS benchmark and the BrainScores between model activations and fMRI data. While larger models generally performed better on both metrics, BrainScores did not significantly improve after fine-tuning.
@article{arxiv.2411.15386,
title = {Inducing Human-like Biases in Moral Reasoning Language Models},
author = {Artem Karpov and Seong Hah Cho and Austin Meek and Raymond Koopmanschap and Lucy Farnik and Bogdan-Ionut Cirstea},
journal= {arXiv preprint arXiv:2411.15386},
year = {2024}
}
Comments
Accepted to the 2nd Workshop on Unifying Representations in Neural Models (UniReps) at NeurIPS 2024