Related papers: MetaAligner: Towards Generalizable Multi-Objective…

Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like Reinforcement Learning with Human Feedback (RLHF) face notable challenges. These approaches require high-quality datasets of positive…

When aligning large language models (LLMs), their performance on various tasks (such as being helpful, harmless, and honest) depends heavily on the composition of their training data. However, selecting a data mixture that achieves strong…

Large language models have emerged as a promising approach towards achieving general-purpose AI agents. The thriving open-source LLM community has greatly accelerated the development of agents that support human-machine dialogue interaction…

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment…

Large language models (LLMs) have substantially advanced machine learning research, including natural language processing, computer vision, data mining, etc., yet they still exhibit critical limitations in explainability, reliability,…

Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are…

A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally,…

Given the broad capabilities of large language models, it should be possible to work towards a general-purpose, text-based assistant that is aligned with human values, meaning that it is helpful, honest, and harmless. As an initial foray in…

Multi-objective optimization problems (MOPs) are ubiquitous in real-world applications, presenting a complex challenge of balancing multiple conflicting objectives. Traditional evolutionary algorithms (EAs), though effective, often rely on…

Multi-objective learning endeavors to concurrently optimize multiple objectives using a single model, aiming to achieve high and balanced performance across diverse objectives. However, this often entails a more complex optimization…

Tool learning is increasingly important for large language models (LLMs) to effectively coordinate and utilize a diverse set of tools in order to solve complex real-world tasks. By selecting and integrating appropriate tools, LLMs extend…

Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically alignment requires fine-tuning a model, which is…

Multiperspective Fusion (MPF) is a novel posttraining alignment framework for large language models (LLMs) developed in response to the growing need for easy bias mitigation. Built on top of the SAGED pipeline, an automated system for…

Alignment of Large Language Models (LLMs) is the ability to satisfy desired objectives during generation, which is critical for trustworthy deployment. In practice, alignment is often operationalized through multiple objectives such as…

Large language models (LLMs) are increasingly used in learning algorithms, evaluations, and optimization tasks. Recent studies have shown that using LLM-based optimizers to automatically optimize model prompts, demonstrations, predictions…

Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the necessity of…

Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these…

Language models trained on large-scale corpus often generate content that is harmful, toxic, or contrary to human preferences, making their alignment with human values a critical concern. Reinforcement learning from human feedback (RLHF)…

Learning generalizable reward functions is a core challenge in embodied intelligence. Recent work leverages contrastive vision language models (VLMs) to obtain dense, domain-agnostic rewards without human supervision. These methods adapt…

Big models, exemplified by Large Language Models (LLMs), are models typically pre-trained on massive data and comprised of enormous parameters, which not only obtain significantly improved performance across diverse tasks but also present…