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.

Similar Papers

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024.acl-long)

Copied to clipboard

Challenge: Reinforcement Learning from Human Feedback (RLHF) relies on scalar rewards to capture user preferences.
Approach: They propose a framework that integrates multi-objective reward modeling to represent diverse preference profiles.
Outcome: The proposed method improves performance across reward objectives and targets.
Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing safety alignment methods for Large Language Models (LLMs) face the distribution shift issue, which requires significant computational resources.
Approach: They propose a framework that leverages the model’s intrinsic safety judgment capability to extract reward signals, which are then used to calculate label confidence for preference reordering.
Outcome: The proposed framework improves safety performance while avoiding 300x computational overheads.
RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Reinforcement learning with human feedback (RLHF) is widely employed to align large language models with user intent.
Approach: They propose to combine rejection sampling and direct preference optimization to improve alignment with user intent by identifying pairs of contrastive samples from human annotator and alternative LLMs.
Outcome: The proposed method outperforms existing methods including RS, PPO, and DPO in a limited resource environment.
Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to align English LLMs with human preferences rely on expensive human annotations or advanced multilingual preference alignment models.
Approach: They propose a method that captures learned preferences from English models by implicit rewards . they annotate preference relations in cross-lingual instruction-following pairs using English .
Outcome: The proposed approach captures learned preferences from well-aligned English models by implicit rewards and transfers them to other languages through iterative training.
Weights-Rotated Preference Optimization for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to align large language models with high reward hacking are limited by the complexity of the parameter space and the complexity.
Approach: They propose a weights-rotated preference optimization algorithm that constrains the output layer logits with the KL divergence inherited from DPO and fine-tunes the intermediate hidden states.
Outcome: The proposed algorithm achieves a 3.27-point improvement on AlpacaEval 2 and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters.
Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts (2024.findings-emnlp)

Copied to clipboard

Challenge: Reinforcement learning from human feedback (RLHF) is the primary method for aligning large language models with human preferences.
Approach: They propose to train an Absolute-Rating Multi-Objective Reward Model with multi-dimensional absolute-rating data.
Outcome: The proposed model outperforms the LLM-as-a-judge method on RewardBench . it achieves state-of-the-art performance on the benchmark .
Reinforcement Learning for Large Language Models via Group Preference Reward Shaping (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for fine-tuning Large Language Models (LLMs) are expensive and sensitive to reward model quality.
Approach: They propose a method that leverages preference-based comparisons rather than precise numerical rewards.
Outcome: Experiments show that GPRS outperforms critic-model-free RL algorithms on RLHF and reasoning tasks.
Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Direct Preference Optimization (DPO) eliminates complex reward modeling in aligning large language models with human preferences, but its online variant faces significant efficiency bottlenecks due to costly real-time preference sampling and the reward model annotation.
Approach: They propose a framework that transforms static datasets into dynamically adaptive equivalents without the need for an explicit reward model.
Outcome: The proposed approach matches or exceeds the performance of a fully online DPO.
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.
MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples (2025.coling-main)

Copied to clipboard

Challenge: Existing preference optimization methods such as DPO and KTO are inherently derived from PPO, requiring a reference model that adds GPU memory resources and relies heavily on abundant preference data.
Approach: They propose an algorithm that leverages the average likelihood of model responses to fit the reward function and maximizes the utilization of preference data.
Outcome: The proposed algorithm outperforms DPO, ORPO, and SimPO on MT-Bench and Arena-Hard.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations