Contextual Moral Value Alignment Through Context-Based Aggregation
This addresses the challenge of value-aligned AI agents in LLMs, which is crucial for developing ethical AI systems, though it appears incremental as it builds on existing alignment methods.
The paper tackles the problem of consolidating multiple independently trained dialogue agents, each aligned with a distinct moral value, into a unified system that adapts to multiple moral values through contextual aggregation, showing better alignment to human values compared to state-of-the-art methods.
Developing value-aligned AI agents is a complex undertaking and an ongoing challenge in the field of AI. Specifically within the domain of Large Language Models (LLMs), the capability to consolidate multiple independently trained dialogue agents, each aligned with a distinct moral value, into a unified system that can adapt to and be aligned with multiple moral values is 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 respond to a user input, taking into account features extracted from the user's input. The proposed system shows better results in term of alignment to human value compared to the state of the art.