English
Related papers

Related papers: The Multilingual Alignment Prism: Aligning Global …

200 papers

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…

Machine Learning · Computer Science 2024-12-19 Katarzyna Kobalczyk , Claudio Fanconi , Hao Sun , Mihaela van der Schaar

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…

Machine Learning · Computer Science 2026-04-21 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran

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…

Artificial Intelligence · Computer Science 2024-12-25 Dan Shi , Tianhao Shen , Yufei Huang , Zhigen Li , Yongqi Leng , Renren Jin , Chuang Liu , Xinwei Wu , Zishan Guo , Linhao Yu , Ling Shi , Bojian Jiang , Deyi Xiong

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…

Artificial Intelligence · Computer Science 2026-05-22 Andrii Kryshtal

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…

Artificial Intelligence · Computer Science 2025-02-18 Maarten Buyl , Hadi Khalaf , Claudio Mayrink Verdun , Lucas Monteiro Paes , Caio C. Vieira Machado , Flavio du Pin Calmon

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…

Computation and Language · Computer Science 2022-10-11 Siyu Lai , Zhen Yang , Fandong Meng , Yufeng Chen , Jinan Xu , Jie Zhou

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,…

Computation and Language · Computer Science 2024-06-21 Wenxuan Wang , Zhaopeng Tu , Chang Chen , Youliang Yuan , Jen-tse Huang , Wenxiang Jiao , Michael R. Lyu

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…

Computation and Language · Computer Science 2024-04-16 Yang Gao , Dana Alon , Donald Metzler

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…

Computation and Language · Computer Science 2025-08-11 Neil Rathi , Dan Jurafsky , Kaitlyn Zhou

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…

Computers and Society · Computer Science 2026-04-23 Travis LaCroix

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…

Computation and Language · Computer Science 2025-05-23 Jia-Nan Li , Jian Guan , Songhao Wu , Wei Wu , Rui Yan

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…

Artificial Intelligence · Computer Science 2024-11-19 Parand A. Alamdari , Toryn Q. Klassen , Rodrigo Toro Icarte , Sheila A. McIlraith

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…

Computation and Language · Computer Science 2023-06-06 Félix Gaschi , Patricio Cerda , Parisa Rastin , Yannick Toussaint

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…

Computation and Language · Computer Science 2024-11-06 Seongyun Lee , Sue Hyun Park , Seungone Kim , Minjoon Seo

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…

Computation and Language · Computer Science 2025-07-22 Kailai Yang , Zhiwei Liu , Qianqian Xie , Jimin Huang , Tianlin Zhang , Sophia Ananiadou

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…

Machine Learning · Computer Science 2024-01-18 Sunayana Rane , Polyphony J. Bruna , Ilia Sucholutsky , Christopher Kello , Thomas L. Griffiths

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.…

Computation and Language · Computer Science 2025-02-14 Jingxin Xu , Guoshun Nan , Sheng Guan , Sicong Leng , Yilian Liu , Zixiao Wang , Yuyang Ma , Zhili Zhou , Yanzhao Hou , Xiaofeng Tao

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…

Computation and Language · Computer Science 2025-10-08 Kehua Feng , Keyan Ding , Yuhao Wang , Menghan Li , Fanjunduo Wei , Xinda Wang , Qiang Zhang , Huajun Chen

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…