Contextual Moral Value Alignment Through Context-Based Aggregation
Abstract: Developing value-aligned agents is a complex undertaking and an ongoing challenge in the field of AI.
Specifically within the domain of Large Language Models (LLMs), designing models that can balance multiple possibly conflicting moral values based on the context is a problem of paramount importance.
In this paper, we propose a system that does contextual moral value alignment based on contextual aggregation. Here, aggregation is defined as the process of integrating a subset of LLM responses that are best suited to a user's input, taking into account features extracted about the user's moral preferences.
The proposed system trained using the Moral Integrity Corpus shows better results in term of alignment to human values compared to state-of-the-art baselines.
Paper Type: Long
Research Area: Ethics, Bias, and Fairness
Research Area Keywords: Moral Values; Model Alignment; Values Alignment
Contribution Types: Model analysis & interpretability
Languages Studied: English
Submission Number: 1842
Loading