# MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time

arXiv: https://arxiv.org/abs/2410.14184 · HTML: https://mlsanity.com/paper/2410.14184/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 22 of 22)

- [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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization](https://mlsanity.com/paper/2311.09096/) (2023)
- [ARGS: Alignment as Reward-Guided Search](https://mlsanity.com/paper/2402.01694/) (2024)
- [InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance](https://mlsanity.com/paper/2401.11206/) (2024)
- [ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition](https://mlsanity.com/paper/2402.15220/) (2024)
- [The Wisdom of Hindsight Makes Language Models Better Instruction Followers](https://mlsanity.com/paper/2302.05206/) (2023)
- [Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback](https://mlsanity.com/paper/2401.11458/) (2024)

## Built on by (most cited first, 5 of 5)

- [LongSafety: Enhance Safety for Long-Context LLMs](https://mlsanity.com/paper/2411.06899/) (2024)
- [Aligning VLM Assistants with Personalized Situated Cognition](https://mlsanity.com/paper/2506.00930/) (2025)
- [SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning](https://mlsanity.com/paper/2511.16324/) (2025)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets](https://mlsanity.com/paper/2509.14738/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential. Existing alignment techniques, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), typically embed predefined preferences directly within the model's parameters. These methods, however, often result in a static alignment that can not account for the diversity of human preferences in practical applications. In response to this challenge, we propose an effective method, MetaAlign, which aims to help LLMs dynamically align with various explicit or implicit preferences specified at inference time. Experimental results show that LLMs optimized on our meticulously constructed MetaAlign Dataset can effectively align with any preferences specified at the inference stage, validating the feasibility of MetaAlign. We hope that our work can provide some insights into the alignment of language models.