English
Related papers

Related papers: Are the Values of LLMs Structurally Aligned with H…

200 papers

Human evaluation is indispensable and inevitable for assessing the quality of texts generated by machine learning models or written by humans. However, human evaluation is very difficult to reproduce and its quality is notoriously unstable,…

Computation and Language · Computer Science 2023-05-04 Cheng-Han Chiang , Hung-yi Lee

Recent advances in aligning Large Language Models with human preferences have benefited from larger reward models and better preference data. However, most of these methodologies rely on the accuracy of the reward model. The reward models…

Artificial Intelligence · Computer Science 2024-11-01 Debangshu Banerjee , Aditya Gopalan

Despite their global prevalence, many Large Language Models (LLMs) are aligned to a monolithic, often Western-centric set of values. This paper investigates the more challenging task of fine-grained value alignment: examining whether LLMs…

Computers and Society · Computer Science 2026-04-15 Bryan Chen Zhengyu Tan , Zhengyuan Liu , Xiaoyuan Yi , Jing Yao , Xing Xie , Nancy F. Chen , Roy Ka-Wei Lee

Large language models (LLMs) have shown various ability on natural language processing, including problems about causality. It is not intuitive for LLMs to command causality, since pretrained models usually work on statistical associations,…

Computation and Language · Computer Science 2024-08-27 Chenyang Zhang , Haibo Tong , Bin Zhang , Dongyu Zhang

Fine-tuning Large Language Models (LLMs) incurs considerable training costs, driving the need for data-efficient training with optimised data ordering. Human-inspired strategies offer a solution by organising data based on human learning…

Computation and Language · Computer Science 2024-11-06 Yushi Yang , Andrew M. Bean , Robert McCraith , Adam Mahdi

While large language models (LLMs) play increasingly significant roles in society, research shows they continue to generate content that reflects social bias against sensitive groups. Existing benchmarks effectively identify these biases,…

Computation and Language · Computer Science 2026-03-12 Tian Xie , Tongxin Yin , Vaishakh Keshava , Xueru Zhang , Siddhartha Reddy Jonnalagadda

Large Language Models (LLMs) have revolutionised the capability of AI models in comprehending and generating natural language text. They are increasingly being used to empower and deploy agents in real-world scenarios, which make decisions…

Artificial Intelligence · Computer Science 2024-08-21 Sagar Uprety , Amit Kumar Jaiswal , Haiming Liu , Dawei Song

Despite Large Language Models' remarkable capabilities, understanding their internal representations remains challenging. Mechanistic interpretability tools such as sparse autoencoders (SAEs) were developed to extract interpretable features…

Machine Learning · Computer Science 2026-01-06 Xiangchen Song , Jiaqi Sun , Zijian Li , Yujia Zheng , Kun Zhang

Large Language Models (LLMs) aim to serve as versatile assistants aligned with human values, as defined by the principles of being helpful, honest, and harmless (hhh). However, in terms of Multimodal Large Language Models (MLLMs), despite…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Zhelun Shi , Zhipin Wang , Hongxing Fan , Zaibin Zhang , Lijun Li , Yongting Zhang , Zhenfei Yin , Lu Sheng , Yu Qiao , Jing Shao

Offering a promising solution to the scalability challenges associated with human evaluation, the LLM-as-a-judge paradigm is rapidly gaining traction as an approach to evaluating large language models (LLMs). However, there are still many…

Computation and Language · Computer Science 2025-08-19 Aman Singh Thakur , Kartik Choudhary , Venkat Srinik Ramayapally , Sankaran Vaidyanathan , Dieuwke Hupkes

Prior research has revealed that certain abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English. In this paper, we extend this investigation to a multilingual…

Computation and Language · Computer Science 2024-10-03 Shaoyang Xu , Weilong Dong , Zishan Guo , Xinwei Wu , Deyi Xiong

Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles. Value-based approaches offer a more principled path,…

Artificial Intelligence · Computer Science 2026-02-04 Woojin Kim , Sieun Hyeon , Jusang Oh , Jaeyoung Do

Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic systems avoid. To bridge this gap, we introduce a formal logic…

Machine Learning · Computer Science 2026-02-02 Chuxue Cao , Jinluan Yang , Haoran Li , Kunhao Pan , Zijian Zhao , Zhengyu Chen , Yuchen Tian , Lijun Wu , Conghui He , Sirui Han , Yike Guo

The wide exploration of large language models (LLMs) raises the awareness of alignment between healthcare stakeholder preferences and model outputs. This alignment becomes a crucial foundation to empower the healthcare workflow effectively,…

Computers and Society · Computer Science 2025-05-07 Kexin Ding , Mu Zhou , Akshay Chaudhari , Shaoting Zhang , Dimitris N. Metaxas

The widespread application of LLMs across various tasks and fields has necessitated the alignment of these models with human values and preferences. Given various approaches of human value alignment, there is an urgent need to understand…

Computation and Language · Computer Science 2025-03-27 Samuel Cahyawijaya , Delong Chen , Yejin Bang , Leila Khalatbari , Bryan Wilie , Ziwei Ji , Etsuko Ishii , Pascale Fung

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Computation and Language · Computer Science 2025-12-08 Zirui He , Mingyu Jin , Bo Shen , Ali Payani , Yongfeng Zhang , Mengnan Du

Humans constantly generate a diverse range of tasks guided by internal motivations. While generative agents powered by large language models (LLMs) aim to simulate this complex behavior, it remains uncertain whether they operate on similar…

Artificial Intelligence · Computer Science 2026-01-29 Yi-Long Lu , Jiajun Song , Chunhui Zhang , Wei Wang

While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority…

Computation and Language · Computer Science 2025-10-28 Yijiang River Dong , Tiancheng Hu , Yinhong Liu , Ahmet Üstün , Nigel Collier

Improving the alignment of Large Language Models (LLMs) with respect to the cultural values that they encode has become an increasingly important topic. In this work, we study whether we can exploit existing knowledge about cultural values…

Computation and Language · Computer Science 2025-09-09 Rochelle Choenni , Ekaterina Shutova

In the rapidly evolving field of Explainable Natural Language Processing (NLP), textual explanations, i.e., human-like rationales, are pivotal for explaining model predictions and enriching datasets with interpretable labels. Traditional…

Computation and Language · Computer Science 2025-11-12 Mahdi Dhaini , Juraj Vladika , Ege Erdogan , Zineb Attaoui , Gjergji Kasneci