相关论文: Unlocking Decoding-time Controllability: Gradient-…

While Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, aligning these models with varying human preferences across multiple objectives remains a significant challenge…

Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at training time and rely on additional high-quality data,…

To date, the multi-objective optimization literature has mainly focused on conflicting objectives, studying the Pareto front, or requiring users to balance tradeoffs. Yet, in machine learning practice, there are many scenarios where such…

Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve multiple conflicting objectives, where naive aggregation of preferences can…

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…

Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or require pre-trained…

The multi-objective alignment of Large Language Models (LLMs) is essential for ensuring foundational models conform to diverse human preferences. Current research in this field typically involves either multiple policies or multiple reward…

Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised multilingual encoders can effectively learn cross-lingual representation. Explicit alignment objectives based on bitexts like Europarl or MultiUN have been shown to…

This paper targets the problem of multi-task dense prediction which aims to achieve simultaneous learning and inference on a bunch of multiple dense prediction tasks in a single framework. A core objective in design is how to effectively…

Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs.…

Large language models (LLMs) are increasingly deployed in real-world applications that require careful balancing of multiple, often conflicting, objectives, such as informativeness versus conciseness, or helpfulness versus creativity.…

In machine learning (ML), we often need to choose one among hundreds of trained ML models at hand, based on various objectives such as accuracy, robustness, fairness or scalability. However, it is often unclear how to compare, aggregate…

Recent advancements in large language models (LLMs) focus on aligning to heterogeneous human expectations and values via multi-objective preference alignment. However, existing methods are dependent on the policy model parameters, which…

Aligning large language models (LLMs) with human preferences is critical for enhancing LLMs' safety, helpfulness, humor, faithfulness, etc. Current reinforcement learning from human feedback (RLHF) mainly focuses on a fixed reward learned…

The fairness-accuracy trade-off is a key challenge in NLP tasks. Current work focuses on finding a single "optimal" solution to balance the two objectives, which is limited considering the diverse solutions on the Pareto front. This work…

Real-world problems are often multi-objective with decision-makers unable to specify a priori which trade-off between the conflicting objectives is preferable. Intuitively, building machine learning solutions in such cases would entail…

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises others (e.g., harmlessness) due to the inherent conflicts…

Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from…

Aligning language models (LMs) to human preferences has emerged as a critical pursuit, enabling these models to better serve diverse user needs. Existing methods primarily focus on optimizing LMs for a single reward function, limiting their…

Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, optimizing model outputs to satisfy diverse objectives with…