AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models (2025.findings-acl)
Copied to clipboard
Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Wan Guanglu, Xunliang Cai, Zhi Zheng, Tong Xu
| Challenge: | Existing multi-objective preference alignment methods for large language models face limitations such as auxiliary reward/reference models and computational complexity. |
| Approach: | They propose a framework that achieves dynamic balance across preference dimensions by using dimension-aware generation metrics as implicit rewards. |
| Outcome: | Empirical results show that AMoPO outperforms state-of-the-art methods by 28.5% . |
Similar Papers
Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment (2024.emnlp-main)
Copied to clipboard
Yiju Guo, Ganqu Cui, Lifan Yuan, Ning Ding, Zexu Sun, Bowen Sun, Huimin Chen, Ruobing Xie, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing algorithms for achieving optimal alignment are mostly unidirectional . a recent study suggests that large language models can be ground with evident preferences . |
| Approach: | They propose to ground large language models with evident preferences . they propose to use controllable preference optimization to specify different objectives . |
| Outcome: | The proposed models can provide responses that match various preferences among the ”3H” desiderata. |
From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Current approaches to align large language models assume uniform human preferences, overlooking the diversity inherent in human populations. |
| Approach: | They propose a framework for scalable personalized alignment of large language models . they establish a preference space characterizing psychological and behavioral dimensions . |
| Outcome: | The proposed framework improves on existing methods with an average of 17.06% accuracy gain across four benchmarks and a strong adaptation capability to novel preferences. |
Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. |
| Approach: | They propose a novel algorithm that uses multiple-gradient descent to optimize LLMs with diverse preferences to maximize trade-offs between objectives. |
| Outcome: | The proposed approach incorporates user preferences across different objectives and achieves Pareto solutions that better align with the user’s specific needs. |
Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that acquiring human preferences by comparing generations is not effective for large language models. |
| Approach: | They propose a preference optimization objective that elicits preferences jointly over the instruction-response pairs. |
| Outcome: | The proposed approach outperforms prior preference optimizations by 5.2% and 3.3% in summarization and open-ended dialogue datasets. |
Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for training large language models require additional annotations to adjust to shifted distributions. |
| Approach: | They propose an algorithm that allows LLMs and reward models to update alternatively via a min-max game to improve their alignment. |
| Outcome: | The proposed framework improves existing alignment baselines in terms of LLM helpfulness and harmlessness. |
Self-Guided Alignment: Adaptive Preference Sensing for Multi-Objective Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to align LLMs with diverse human values rely on ground-truth scores . existing approaches implicitly approximate an average-user preference, thereby failing to capture heterogeneity of human values or accommodate conflicting user needs. |
| Approach: | They propose a framework that transforms passive reward dependency into an intrinsic adaptive sensing capability. |
| Outcome: | The proposed framework outperforms state-of-the-art models in multiple model scales and improves preference alignment. |
Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment (2025.coling-main)
Copied to clipboard
| Challenge: | Human values are inherently diverse, making it insufficient to align LLMs solely with general preferences. |
| Approach: | They propose a flexible paradigm for individual preference alignment that disentangles preference representation from text generation in LLMs. |
| Outcome: | The proposed method produces aligned quality and better than PEFT-based methods while reducing training time for each new individual preference by 80% to 90%. |
Comparison-based Active Preference Learning for Multi-dimensional Personalization (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models have shown remarkable success, but aligning them with human preferences remains a core challenge. |
| Approach: | They propose to capture implicit user preferences from comparative feedback to improve model performance. |
| Outcome: | The proposed framework is able to capture implicit user preferences from comparative feedback. |
Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent approaches to language model alignment assume homogeneous human preferences, but actual human preferences vary widely and are hard to satisfy with a single language model. |
| Approach: | They propose an RL-free extension of Direct Preference Optimization (DPO) that folds language modeling directly into reward modeling and trains language models as collective reward models that combine all objectives with specific weights. |
| Outcome: | The proposed method matches or outperforms existing methods in safety alignment and long-form question answering. |
On Diversified Preferences of Large Language Model Alignment (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) can be fine tuned with human feedback, but human preferences can be diversified due to annotators’ different tastes, which hinders the effectiveness of LLM alignment methods. |
| Approach: | They propose a calibration error metric to evaluate large language models (LLMs) and a multi-objective reward learning method to enhance the calibration performance of RMs on shared preferences. |
| Outcome: | The proposed model can be adopted as a key calibration error and MORE can achieve superior alignment performance. |