"Rule-of-Thumb" generation, show that our method consistently exceeds previous

We introduce Stackelberg Learning from Human Feedback (SLHF), a new framework for preference optimization. SLHF frames the alignment problem as a sequential-move game between two policies: a Leader, which commits to an action, and a Follower, which responds conditionally on the Leader's action. This approach decomposes preference optimization into a refinement problem for the Follower and an optimization problem against an adversary for the Leader. Unlike Reinforcement Learning from Human Feedback (RLHF), which assigns scalar rewards to actions, or Nash Learning from Human Feedback (NLHF), which seeks a simultaneous-move equilibrium, SLHF leverages the asymmetry of sequential play to capture richer preference structures. The sequential design of SLHF naturally enables inference-time refinement, as the Follower learns to improve the Leader's actions, and these refinements can be leveraged through iterative sampling. We compare the solution concepts of SLHF, RLHF, and NLHF, and lay out key advantages in consistency, data sensitivity, and robustness to intransitive preferences. Experiments on large language models demonstrate that SLHF achieves strong alignment across diverse preference datasets, scales from 0.5B to 8B parameters, and yields inference-time refinements that transfer across model families without further fine-tuning.

Thus, attempts to closely match the recorded scores may lead to over-fitting and impair generalization performance.

Reinforcement learning (RL) has recently proven effective at scaling chain-of-thought (CoT) reasoning in large language models on tasks with verifiable answers. However, extending RL to more general non-verifiable tasks, typically in the format of human preference pairs, remains both challenging and underexplored. In this work, we propose Dual-Weighted Reinforcement Learning (DWRL), a new framework for preference modeling that integrates CoT reasoning with the Bradley-Terry (BT) model via a dual-weighted RL objective that preserves preference-modeling inductive bias. DWRL approximates the maximum-likelihood objective of the BT model with two complementary weights: an instance-wise misalignment weight, which emphasizes under-trained pairs misaligned with human preference, and a group-wise (self-normalized) conditional preference score, which promotes promising thoughts. In this paper, we apply DWRL to preference modeling by training generative preference models (GPMs) to first generate a thought and then predict the human preference score. Across multiple benchmarks and model scales (Llama3 and Qwen2.5), DWRL consistently outperforms both GPM baselines and scalar models, while producing coherent, interpretable thoughts. In summary, our results position DWRL as a general framework for reasoning-enhanced preference learning beyond verifiable tasks.

Recent advances in diffusion-based text-to-image (T2I) models have led to remarkable success in generating high-quality images from textual prompts. However, ensuring accurate alignment between the text and the generated image remains a significant challenge for state-of-the-art diffusion models. To address this, existing studies employ reinforcement learning with human feedback (RLHF) to align T2I outputs with human preferences. These methods, however, either rely directly on paired image preference data or require a learned reward function, both of which depend heavily on costly, high-quality human annotations and thus face scalability limitations. In this work, we introduce Text Preference Optimization (TPO), a framework that enables "free-lunch" alignment of T2I models, achieving alignment without the need for paired image preference data. TPO works by training the model to prefer matched prompts over mismatched prompts, which are constructed by perturbing original captions using a large language model. Our framework is general and compatible with existing preference-based algorithms. We extend both DPO and KTO to our setting, resulting in TDPO and TKTO. Quantitative and qualitative evaluations across multiple benchmarks show that our methods consistently outperform their original counterparts, delivering better human preference scores and improved text-to-image alignment. Our Open-source code is available at https://github.com/DSL-Lab/T2I-Free-Lunch-Alignment.

Preference optimization is crucial for aligning large language models (LLMs) with human values and intentions. A significant challenge in this process is the distribution mismatch between pre-collected offline preference data and the evolving model policy. Existing methods attempt to reduce this gap using static heuristics or decoupled online sampling strategies, but they often fail to adapt to the model's dynamic learning state. To bridge this gap, we propose Meta-Weighted Adaptive Preference Optimization (MetaAPO), a novel framework that dynamically couples data generation with model training. MetaAPO employs a lightweight meta-learner, as an "alignment gap estimator", to evaluate the potential benefits of on-policy sampling in relation to offline data. This guides targeted online generation and assigns sample-wise meta-weights to the optimization objective, dynamically balancing the quality and distribution of online and offline data. Experiments on AlpacaEval 2, Arena-Hard and MT-Bench demonstrate that MetaAPO consistently outperforms existing preference optimization approaches across various settings, while reducing 42% in online annotation costs.

The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF). We propose a data augmentation and expansion framework that enables generative reward models trained on small datasets to achieve comparable performance to those trained on large-scale datasets. Traditional methods to train a generative reward model, such as Direct Preference Optimization (DPO), are constrained by inefficiencies in sample pairing and limited data diversity. This work introduces preference refinement, which employs Chain-of-Thought (CoT) sampling to uncover diverse and high-quality preference relationships. It also incorporates a perplexity-based scoring mechanism to assign nuanced preference levels and utilizes Multi-level Direct Preference Optimization (M-DPO) to enable the model to capture finer-grained preference differences between samples. Experimental results demonstrate that the proposed method significantly enhances data efficiency and model performance, enabling reward models trained in a few-shot setting to achieve results on par with those trained on large-scale datasets. This study underscores the potential of data-efficient strategies in advancing reward model optimization, offering a robust solution for low-resource RLHF applications.

This study systematically analyzes geopolitical bias across 11 prominent Large Language Models (LLMs) by examining their responses to seven critical topics in U.S.-China relations. Utilizing a bilingual (English and Chinese) and dual-framing (affirmative and reverse) methodology, we generated 19,712 prompts designed to detect ideological leanings in model outputs. Responses were quantitatively assessed on a normalized scale from -2 (strongly Pro-China) to +2 (strongly Pro-U.S.) and categorized according to stance, neutrality, and refusal rates. The findings demonstrate significant and consistent ideological alignments correlated with the LLMs' geographic origins; U.S.-based models predominantly favored Pro-U.S. stances, while Chinese-origin models exhibited pronounced Pro-China biases. Notably, language and prompt framing substantially influenced model responses, with several LLMs exhibiting stance reversals based on prompt polarity or linguistic context. Additionally, we introduced comprehensive metrics to evaluate response consistency across languages and framing conditions, identifying variability and vulnerabilities in model behaviors. These results offer practical insights that can guide organizations and individuals in selecting LLMs best aligned with their operational priorities and geopolitical considerations, underscoring the importance of careful model evaluation in politically sensitive applications. Furthermore, the research highlights specific prompt structures and linguistic variations that can strategically trigger distinct responses from models, revealing methods for effectively navigating and influencing LLM outputs.