相关论文: The Multilingual Alignment Prism: Aligning Global …

As large language models (LLMs) become increasingly embedded in everyday applications, ensuring their alignment with the diverse preferences of individual users has become a critical challenge. Currently deployed approaches typically assume…

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and…

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…

The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing…

AI models are already deployed in societies affected by armed conflict, and journalists, humanitarian workers, governments and ordinary citizens rely on them for information or for their work processes. No established practice exists for…

In AI alignment, extensive latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are `better' or `safer.' We refer to this latitude as alignment discretion. Such discretion remains largely…

Word alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded substantial improvements by…

Safety lies at the core of developing and deploying large language models (LLMs). However, previous safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. In this work,…

A key requirement in developing Generative Language Models (GLMs) is to have their values aligned with human values. Preference-based alignment is a widely used paradigm for this purpose, in which preferences over generation pairs are first…

As large language models (LLMs) are deployed globally, it is crucial that their responses are calibrated across languages to accurately convey uncertainty and limitations. Prior work shows that LLMs are linguistically overconfident in…

The value alignment problem for artificial intelligence (AI) is often framed as a purely technical or normative challenge, sometimes focused on hypothetical future systems. I argue that the problem is better understood as a structural…

Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in user values and needs. This paper introduces a comprehensive…

Pluralistic alignment is concerned with ensuring that an AI system's objectives and behaviors are in harmony with the diversity of human values and perspectives. In this paper we study the notion of pluralistic alignment in the context of…

Without any explicit cross-lingual training data, multilingual language models can achieve cross-lingual transfer. One common way to improve this transfer is to perform realignment steps before fine-tuning, i.e., to train the model to build…

Although humans inherently have diverse values, current large language model (LLM) alignment methods often assume that aligning LLMs with the general public's preferences is optimal. A major challenge in adopting a more individualized…

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…

Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is…

Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human intentions, ensuring the outputs are harmless and helpful.…

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Recent advances in general-purpose AI underscore the urgent need to align AI systems with human goals and values. Yet, the lack of a clear, shared understanding of what constitutes "alignment" limits meaningful progress and…