Utkarsh Agarwal — accepted AI-conference papers

2024

Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language We Prompt Them in

Utkarsh Agarwal, Kumar Tanmay, Aditi Khandelwal, Monojit Choudhury

COLING 2024main

Ethical reasoning is a crucial skill for Large Language Models (LLMs). However, moral values are not universal, but rather influenced by language and culture. This paper explores how three prominent LLMs – GPT-4, ChatGPT, and Llama2Chat-70B – perform ethical reasoning in different languages and if t…

Cited by 20 Source ↗PDF ↗Scholar ↗

2023

Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs

Abhinav Sukumar Rao, Aditi Khandelwal, Kumar Tanmay, Utkarsh Agarwal, Monojit Choudhury

EMNLP 2023long findings

In this position paper, we argue that instead of morally aligning LLMs to specific set of ethical principles, we should infuse generic ethical reasoning capabilities into them so that they can handle value pluralism at a global scale. When provided with an ethical policy, an LLM should be capable of…

Cited by 0 Source ↗Scholar ↗