# Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts

arXiv: https://arxiv.org/abs/2408.05094 · HTML: https://mlsanity.com/paper/2408.05094/

## Key facts

- Cited by 9 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 38 of its 56 references that are in the map.
- First posted on arXiv 9 Aug 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, 30 of 38)

- [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 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (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)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding](https://mlsanity.com/paper/2402.08983/) (2024)
- [Quark: Controllable Text Generation with Reinforced Unlearning](https://mlsanity.com/paper/2205.13636/) (2022)
- [Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2](https://mlsanity.com/paper/2311.10702/) (2023)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment](https://mlsanity.com/paper/2402.10207/) (2024)
- [Platypus: Quick, Cheap, and Powerful Refinement of LLMs](https://mlsanity.com/paper/2308.07317/) (2023)
- [Black-Box Prompt Optimization: Aligning Large Language Models without Model Training](https://mlsanity.com/paper/2311.04155/) (2023)
- [Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment](https://mlsanity.com/paper/2402.19085/) (2024)
- [Confronting Reward Model Overoptimization with Constrained RLHF](https://mlsanity.com/paper/2310.04373/) (2023)
- [Aligning to Thousands of Preferences via System Message Generalization](https://mlsanity.com/paper/2405.17977/) (2024)
- [Panacea: Pareto Alignment via Preference Adaptation for LLMs](https://mlsanity.com/paper/2402.02030/) (2024)
- [Alleviating Hallucinations of Large Language Models through Induced Hallucinations](https://mlsanity.com/paper/2312.15710/) (2023)
- [Decoding-time Realignment of Language Models](https://mlsanity.com/paper/2402.02992/) (2024)

## Built on by (most cited first, 9 of 9)

- [Learning Safety Constraints for Large Language Models](https://mlsanity.com/paper/2505.24445/) (2025)
- [Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization](https://mlsanity.com/paper/2512.11391/) (2025)
- [Robust Multi-Objective Controlled Decoding of Large Language Models](https://mlsanity.com/paper/2503.08796/) (2025)
- [ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data](https://mlsanity.com/paper/2504.16628/) (2025)
- [A Survey on Training-free Alignment of Large Language Models](https://mlsanity.com/paper/2508.09016/) (2025)
- [VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models](https://mlsanity.com/paper/2603.18113/) (2026)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion](https://mlsanity.com/paper/2604.18106/) (2026)
- [Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary](https://mlsanity.com/paper/2607.18553/) (2026)

## Abstract (arXiv)

The task of multi-objective alignment aims at balancing and controlling the different alignment objectives (e.g., helpfulness, harmlessness and honesty) of large language models to meet the personalized requirements of different users. However, previous methods tend to train multiple models to deal with various user preferences, with the number of trained models growing linearly with the number of alignment objectives and the number of different preferences. Meanwhile, existing methods are generally poor in extensibility and require significant re-training for each new alignment objective considered. Considering the limitation of previous approaches, we propose MCA (Multi-objective Contrastive Alignemnt), which constructs an expert prompt and an adversarial prompt for each objective to contrast at the decoding time and balances the objectives through combining the contrast. Our approach is verified to be superior to previous methods in obtaining a well-distributed Pareto front among different alignment objectives.