# Align on the Fly: Adapting Chatbot Behavior to Established Norms

arXiv: https://arxiv.org/abs/2312.15907 · HTML: https://mlsanity.com/paper/2312.15907/

## Key facts

- Cited by 23 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 42 of its 63 references that are in the map.
- First posted on arXiv 26 Dec 2023.

## Placed in

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

## Builds on (most cited first, 30 of 42)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)

## Built on by (most cited first, 23 of 23)

- [RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation](https://mlsanity.com/paper/2404.00610/) (2024)
- [Decoding-Time Language Model Alignment with Multiple Objectives](https://mlsanity.com/paper/2406.18853/) (2024)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [Towards Human-centered Proactive Conversational Agents](https://mlsanity.com/paper/2404.12670/) (2024)
- [Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback](https://mlsanity.com/paper/2501.12895/) (2025)
- [Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling](https://mlsanity.com/paper/2403.01251/) (2024)
- [A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models](https://mlsanity.com/paper/2504.07070/) (2025)
- [On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models](https://mlsanity.com/paper/2403.04204/) (2024)
- [Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues](https://mlsanity.com/paper/2402.01737/) (2024)
- [Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction](https://mlsanity.com/paper/2405.13432/) (2024)
- [Towards a Unified View of Preference Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2409.02795/) (2024)
- [The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment](https://mlsanity.com/paper/2412.16468/) (2024)
- [LLMCRIT: Teaching Large Language Models to Use Criteria](https://mlsanity.com/paper/2403.01069/) (2024)
- [ProgressGym: Alignment with a Millennium of Moral Progress](https://mlsanity.com/paper/2406.20087/) (2024)
- [LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization](https://mlsanity.com/paper/2509.17183/) (2025)
- [Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness](https://mlsanity.com/paper/2409.10825/) (2024)
- [Evaluating Usability and Engagement of Large Language Models in Virtual Reality for Traditional Scottish Curling](https://mlsanity.com/paper/2408.09285/) (2024)
- [AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference](https://mlsanity.com/paper/2505.13531/) (2025)
- [SAFETY-J: Evaluating Safety with Critique](https://mlsanity.com/paper/2407.17075/) (2024)
- [PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization](https://mlsanity.com/paper/2507.16679/) (2025)
- [A Survey on Training-free Alignment of Large Language Models](https://mlsanity.com/paper/2508.09016/) (2025)
- [Examining the Role of Relationship Alignment in Large Language Models](https://mlsanity.com/paper/2410.01708/) (2024)
- [Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization](https://mlsanity.com/paper/2503.07660/) (2025)

## Abstract (arXiv)

In this paper, we aim to align large language models with the ever-changing, complex, and diverse human values (e.g., social norms) across time and locations. This presents a challenge to existing alignment techniques, such as supervised fine-tuning, which internalize values within model parameters. To overcome this, we propose an On-the-fly Preference Optimization (OPO) method, which is a real-time alignment that works in a streaming way. It employs an external memory to store established rules for alignment, which can constrain LLMs' behaviors without further training, allowing for convenient updates and customization of human values. We also introduce a scalable evaluation to assess the proposed method more effectively. Experimental results on both human-annotated and auto-generated questions from legal and moral domains indicate the effectiveness of the proposed OPO method. Our code and data are released at https://github.com/GAIR-NLP/OPO.