Can I read Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses on EtoBox?

Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses by Senthilkumar, Pranav; Balasubramanian, Visshwa; Jain, Prisha; Maity, Aneesa; Lu, Jonathan; Zhu, Kevin is a scholarly article available to read on EtoBox.

What is Fine-Tuning Language Models for Ethical Ambiguity: A Comparative Study of Alignment with Human Responses about?

Language models often misinterpret human intentions due to their handling of ambiguity, a limitation well-recognized in NLP research. While morally clear scenarios are more discernible to LLMs, greater difficulty is encountered in morally ambiguous contexts. In this investigation, we explored LLM calibration to show that human and LLM judgments are poorly aligned in such scenarios. We used two curated datasets from the Scruples project for evaluation: DILEMMAS, which involves pairs of distinct moral scenarios to assess the model's ability to compare and contrast ethical situations, and ANECDOTES, which presents individual narratives to evaluate the model's skill in drawing out details, interpreting, and analyzing distinct moral scenarios. Model answer probabilities were extracted for all possible choices and compared with human annotations to benchmark the alignment of three models: Llama-3.1-8b, Zephyr-7b-beta, and Mistral-7b. Significant improvements were observed after fine-tuning, with notable enhancements in both cross-entropy and Dirichlet scores, particularly in the latter. Notably, after fine-tuning, the performance of Mistral-7B-Instruct-v0.3 was on par with GPT-4o. Howeve

Author

Senthilkumar, Pranav; Balasubramanian, Visshwa; Jain, Prisha; Maity, Aneesa; Lu, Jonathan; Zhu, Kevin

Published

2024

Language

EN