English
Related papers

Related papers: Beyond Preferences: Learning Alignment Principles …

200 papers

Recent breakthroughs in generative artificial intelligence (AI) and large language models (LLMs) unravel new capabilities for AI personal assistants to overcome cognitive bandwidth limitations of humans, providing decision support or even…

Artificial Intelligence · Computer Science 2026-02-10 Srijoni Majumdar , Edith Elkind , Evangelos Pournaras

Given that Artificial Intelligence (AI) increasingly permeates our lives, it is critical that we systematically align AI objectives with the goals and values of humans. The human-AI alignment problem stems from the impracticality of…

Computers and Society · Computer Science 2022-07-05 John Nay , James Daily

Artificial Intelligence (AI) is rapidly embedded in critical decision-making systems, however their foundational ``black-box'' models require eXplainable AI (XAI) solutions to enhance transparency, which are mostly oriented to experts,…

Machine Learning · Computer Science 2025-06-17 Eva Paraschou , Ioannis Arapakis , Sofia Yfantidou , Sebastian Macaluso , Athena Vakali

Generative AI (GenAI) is increasingly used in survey contexts to simulate human preferences. While many research endeavors evaluate the quality of synthetic GenAI data by comparing model-generated responses to gold-standard survey results,…

Machine Learning · Computer Science 2025-02-25 Sarah Ball , Simeon Allmendinger , Frauke Kreuter , Niklas Kühl

Generative artificial intelligence (AI) systems based on large-scale pretrained foundation models (PFMs) such as vision-language models, large language models (LLMs), diffusion models and vision-language-action (VLA) models have…

Artificial Intelligence · Computer Science 2025-01-07 Alhassan Mumuni , Fuseini Mumuni

Reinforcement Learning from AI Feedback (RLAIF) enables language models to improve by training on their own preference judgments, yet no theoretical account explains why this self-improvement seemingly works for value learning. We propose…

Machine Learning · Computer Science 2026-03-04 Robin Young

This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns. Our methodology involved using a dataset from a human voting…

Computation and Language · Computer Science 2024-12-20 Joshua C. Yang , Damian Dailisan , Marcin Korecki , Carina I. Hausladen , Dirk Helbing

Are AI systems truly representing human values, or merely averaging across them? Our study suggests a concerning reality: Large Language Models (LLMs) fail to represent diverse cultural moral frameworks despite their linguistic…

Computation and Language · Computer Science 2025-08-01 Simon Münker

As language models continue to grow larger, the cost of acquiring high-quality training data has increased significantly. Collecting human feedback is both expensive and time-consuming, and manual labels can be noisy, leading to an…

Artificial Intelligence · Computer Science 2025-04-08 Xue Zhang

Ensuring the safety of large language models (LLMs) requires robust red teaming, yet the systematic synthesis of high-quality toxic data remains under-explored. We propose Reverse Constitutional AI (R-CAI), a framework for automated and…

Computation and Language · Computer Science 2026-04-21 Yuan Fang , Yiming Luo , Aimin Zhou , Fei Tan

The constitutional framework of alignment aims to align large language models (LLMs) with value-laden principles written in natural language (such as to avoid using biased language). Prior work has focused on parameter fine-tuning…

Computation and Language · Computer Science 2026-01-27 Henry Bell , Caroline Zhang , Mohammed Mobasserul Haque , Dhaval Potdar , Samia Zaman , Brandon Fain

As Artificial Intelligence (AI), particularly Large Language Models (LLMs), becomes increasingly embedded in education systems worldwide, ensuring their ethical, legal, and contextually appropriate deployment has become a critical policy…

Computers and Society · Computer Science 2026-05-27 Sara Alaswad , Tatiana Kalganova , Wasan Awad

Large Language Models (LLMs) enable a future in which certain types of legal documents may be generated automatically. This has a great potential to streamline legal processes, lower the cost of legal services, and dramatically increase…

Human-Computer Interaction · Computer Science 2024-10-11 Jakub Harasta , Tereza Novotná , Jaromir Savelka

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

Artificial Intelligence · Computer Science 2026-05-12 Katarzyna Kobalczyk , Mihaela van der Schaar

This paper introduces an approach to increasing the explainability of artificial intelligence (AI) systems by embedding Large Language Models (LLMs) within standardized analytical processes. While traditional explainable AI (XAI) methods…

Artificial Intelligence · Computer Science 2025-11-11 Marc Jansen , Marcel Pehlke

Human decision makers increasingly delegate choices to AI agents, raising a natural question: does the AI implement the human principal's preferences or pursue its own? To study this question using revealed preference techniques, I…

Theoretical Economics · Economics 2026-03-31 Elchin Suleymanov

In this paper, we conduct an empirical analysis of how large language models (LLMs), specifically GPT-4, interpret constitutional principles in complex decision-making scenarios. We examine rulings from the Italian Constitutional Court on…

Computation and Language · Computer Science 2024-08-12 Camilla Bignotti , Carolina Camassa

The adoption of generative AI technologies is swiftly expanding. Services employing both linguistic and mul-timodal models are evolving, offering users increasingly precise responses. Consequently, human reliance on these technologies is…

Computers and Society · Computer Science 2023-11-17 Jaeyoun You , Bongwon Suh

Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reveal little about the value priorities these systems express or how those priorities…

Artificial Intelligence · Computer Science 2026-05-19 Gabriel Rongyang Lau , Wei Yan Low , Seow Min Koh , Fiona Fui-Hoon Nah , Andree Hartanto

In aligning large language models (LLMs), utilizing feedback from existing advanced AI rather than humans is an important method to scale supervisory signals. However, it is highly challenging for AI to understand human intentions and…

Computation and Language · Computer Science 2024-06-18 Rong Bao , Rui Zheng , Shihan Dou , Xiao Wang , Enyu Zhou , Bo Wang , Qi Zhang , Liang Ding , Dacheng Tao