# Contextual Moral Value Alignment Through Context-Based Aggregation

arXiv: https://arxiv.org/abs/2403.12805 · HTML: https://mlsanity.com/paper/2403.12805/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 13 of 13)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems](https://mlsanity.com/paper/2204.03021/) (2022)
- [On Diversified Preferences of Large Language Model Alignment](https://mlsanity.com/paper/2312.07401/) (2023)
- [Value Alignment Verification](https://mlsanity.com/paper/2012.01557/) (2020)

## Built on by (most cited first, 10 of 10)

- [Position: Theory of Mind Benchmarks are Broken for Large Language Models](https://mlsanity.com/paper/2412.19726/) (2024)
- [MAP: Multi-Human-Value Alignment Palette](https://mlsanity.com/paper/2410.19198/) (2024)
- [LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory](https://mlsanity.com/paper/2502.20432/) (2025)
- [Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference](https://mlsanity.com/paper/2412.14355/) (2024)
- [EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models](https://mlsanity.com/paper/2510.05942/) (2025)
- [A Survey on Moral Foundation Theory and Pre-Trained Language Models: Current Advances and Challenges](https://mlsanity.com/paper/2409.13521/) (2024)
- [The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2512.22337/) (2025)
- [Mitigating loss of control in advanced AI systems through instrumental goal trajectories](https://mlsanity.com/paper/2602.01699/) (2026)
- [Normative Moral Pluralism for AI: A Framework for Deliberation in Complex Moral Contexts](https://mlsanity.com/paper/2508.08333/) (2025)
- [An Aristotelian ontology of instrumental goals: Structural features to be managed and not failures to be eliminated](https://mlsanity.com/paper/2510.25471/) (2025)

## Abstract (arXiv)

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.