English
Related papers

Related papers: Measuring Value Alignment

200 papers

Risk thresholds provide a measure of the level of risk exposure that a society or individual is willing to withstand, ultimately shaping how we determine the safety of technological systems. Against the backdrop of the Cold War, the first…

Computers and Society · Computer Science 2025-04-22 Heidy Khlaaf , Sarah Myers West

Emerging efforts in AI alignment seek to broaden participation in shaping model behavior by eliciting and integrating collective input into a policy for model finetuning. While pluralistic, these processes are often linear and do not allow…

Human-Computer Interaction · Computer Science 2025-03-18 K. J. Kevin Feng , Inyoung Cheong , Quan Ze Chen , Amy X. Zhang

Agentic artificial intelligence systems are autonomous technologies capable of pursuing complex goals with minimal human oversight and are rapidly emerging as the next frontier in AI. While these systems promise major gains in productivity,…

Computers and Society · Computer Science 2026-01-13 Theodore Roberts , Bahram Zarrin

Planning under uncertainty is a central problem in the study of automated sequential decision making, and has been addressed by researchers in many different fields, including AI planning, decision analysis, operations research, control…

Artificial Intelligence · Computer Science 2011-05-30 C. Boutilier , T. Dean , S. Hanks

As artificial intelligence (AI) becomes deeply integrated into critical infrastructures and everyday life, ensuring its safe deployment is one of humanity's most urgent challenges. Current AI models prioritize task optimization over safety,…

Artificial Intelligence · Computer Science 2024-11-08 Joshua T. S. Hewson

Long-term fairness is an important factor of consideration in designing and deploying learning-based decision systems in high-stake decision-making contexts. Recent work has proposed the use of Markov Decision Processes (MDPs) to formulate…

Machine Learning · Computer Science 2022-10-25 Eric Yang Yu , Zhizhen Qin , Min Kyung Lee , Sicun Gao

Aligning AI agents to human intentions and values is a key bottleneck in building safe and deployable AI applications. But whose values should AI agents be aligned with? Reinforcement learning with human feedback (RLHF) has emerged as the…

Artificial Intelligence · Computer Science 2023-10-25 Abhilash Mishra

As Artificial Intelligence (AI) advances toward Artificial General Intelligence (AGI) and eventually Artificial Superintelligence (ASI), it may potentially surpass human control, deviate from human values, and even lead to irreversible…

There is a growing need for data-driven research efforts on how the public perceives the ethical, moral, and legal issues of autonomous AI systems. The current debate on the responsibility gap posed by these systems is one such example.…

Computers and Society · Computer Science 2021-01-18 Gabriel Lima , Meeyoung Cha

Critical examinations of AI systems often apply principles such as fairness, justice, accountability, and safety, which is reflected in AI regulations such as the EU AI Act. Are such principles sufficient to promote the design of systems…

Human-Computer Interaction · Computer Science 2022-06-16 William Seymour , Max Van Kleek , Reuben Binns , Dave Murray-Rust

Developing value-aligned AI agents is a complex undertaking and an ongoing challenge in the field of AI. Specifically within the domain of Large Language Models (LLMs), the capability to consolidate multiple independently trained dialogue…

This study discusses the interplay between metrics used to measure the explainability of the AI systems and the proposed EU Artificial Intelligence Act. A standardisation process is ongoing: several entities (e.g. ISO) and scholars are…

Artificial Intelligence · Computer Science 2022-01-20 Francesco Sovrano , Salvatore Sapienza , Monica Palmirani , Fabio Vitali

Ensuring that Large Language Models (LLMs) align with the diverse and evolving human values across different regions and cultures remains a critical challenge in AI ethics. Current alignment approaches often yield superficial conformity…

Artificial Intelligence · Computer Science 2025-11-04 Jiahao Wang , Songkai Xue , Jinghui Li , Xiaozhen Wang

One of the major challenges we face with ethical AI today is developing computational systems whose reasoning and behaviour are provably aligned with human values. Human values, however, are notorious for being ambiguous, contradictory and…

Artificial Intelligence · Computer Science 2023-05-05 Nardine Osman , Mark d'Inverno

Aligning large language models (LLMs) typically aim to reflect general human values and behaviors, but they often fail to capture the unique characteristics and preferences of individual users. To address this gap, we introduce the concept…

Computation and Language · Computer Science 2025-03-11 Minjun Zhu , Yixuan Weng , Linyi Yang , Yue Zhang

Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Mean payoff (or long-run average reward) provides a mathematically elegant formalism to express performance related…

Performance · Computer Science 2017-09-08 Jan Křetínský , Tobias Meggendorfer

Generative AI systems (ChatGPT, DALL-E, etc) are expanding into multiple areas of our lives, from art Rombach et al. [2021] to mental health Rob Morris and Kareem Kouddous [2022]; their rapidly growing societal impact opens new…

Artificial Intelligence · Computer Science 2024-05-21 Alexis Roger , Esma Aïmeur , Irina Rish

Large language model-based AI companions are increasingly viewed by users as friends or romantic partners, leading to deep emotional bonds. However, they can generate biased, discriminatory, and harmful outputs. Recently, users are taking…

Human-Computer Interaction · Computer Science 2025-02-14 Xianzhe Fan , Qing Xiao , Xuhui Zhou , Jiaxin Pei , Maarten Sap , Zhicong Lu , Hong Shen

The goal of imitation learning is for an apprentice to learn how to behave in a stochastic environment by observing a mentor demonstrating the correct behavior. Accurate prior knowledge about the correct behavior can reduce the need for…

Machine Learning · Computer Science 2012-06-26 Umar Syed , Robert E. Schapire

Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. Proper alignment of…

Human-Computer Interaction · Computer Science 2025-11-14 Vijay Keswani , Cyrus Cousins , Breanna Nguyen , Vincent Conitzer , Hoda Heidari , Jana Schaich Borg , Walter Sinnott-Armstrong