English
Related papers

Related papers: Concept Alignment

200 papers

This paper introduces the concept of value awareness in AI, which goes beyond the traditional value-alignment problem. Our definition of value awareness presents us with a concise and simplified roadmap for engineering value-aware AI. The…

Artificial Intelligence · Computer Science 2025-12-16 Nardine Osman

Do AI systems truly understand human concepts or merely mimic surface patterns? We investigate this through chess, where human creativity meets precise strategic concepts. Analyzing a 270M-parameter transformer that achieves…

Machine Learning · Computer Science 2025-11-05 Semyon Lomasov , Judah Goldfeder , Mehmet Hamza Erol , Matthew So , Yao Yan , Addison Howard , Nathan Kutz , Ravid Shwartz Ziv

This paper introduces function alignment, a novel theory of mind and intelligence that is both intuitively compelling and structurally grounded. It explicitly models how meaning, interpretation, and analogy emerge from interactions among…

Computation and Language · Computer Science 2025-04-15 Gus G. Xia

For an artificial intelligence (AI) to be aligned with human values (or human preferences), it must first learn those values. AI systems that are trained on human behavior, risk miscategorising human irrationalities as human values -- and…

Artificial Intelligence · Computer Science 2022-03-02 Rebecca Gorman , Stuart Armstrong

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication. However, there is very little work on endowing machines with the ability to form and reason with concepts. In particular,…

Computation and Language · Computer Science 2023-11-06 Chen Shani , Jilles Vreeken , Dafna Shahaf

Over the past decade, AI has made a remarkable progress. It is agreed that this is due to the recently revived Deep Learning technology. Deep Learning enables to process large amounts of data using simplified neuron networks that simulate…

Artificial Intelligence · Computer Science 2015-02-19 Emanuel Diamant

The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive. Many researchers are concerned that AIs and AGIs will harm humans via intentional misuse (AI-misuse)…

Artificial Intelligence · Computer Science 2023-05-31 Catalin Mitelut , Ben Smith , Peter Vamplew

Humans rely more and more on systems with AI components. The AI community typically treats human inputs as a given and optimizes AI models only. This thinking is one-sided and it neglects the fact that humans can learn, too. In this work,…

Human-Computer Interaction · Computer Science 2020-09-22 Johannes Schneider

In this position paper, we argue that understanding the relation between structure in the data distribution and structure in trained models is central to AI alignment. First, we discuss how two neural networks can have equivalent…

This paper critically evaluates the attempts to align Artificial Intelligence (AI) systems, especially Large Language Models (LLMs), with human values and intentions through Reinforcement Learning from Feedback (RLxF) methods, involving…

While much research in artificial intelligence (AI) has focused on scaling capabilities, the accelerating pace of development makes countervailing work on producing harmless, "aligned" systems increasingly urgent. Yet research on alignment…

Artificial Intelligence · Computer Science 2025-12-12 Dani Roytburg , Beck Miller

Though intelligent agents are supposed to improve human experience (or make it more efficient), it is hard from a human perspective to grasp the ethical values which are explicitly or implicitly embedded in an agent behaviour. This is the…

Artificial Intelligence · Computer Science 2025-08-12 Gianluca Bontempi

There is no 'ordinary' when it comes to AI. The human-AI experience is extraordinarily complex and specific to each person, yet dominant measures such as usability scales and engagement metrics flatten away nuance. We argue for AI…

Human-Computer Interaction · Computer Science 2026-03-11 Bhada Yun , Evgenia Taranova , Dana Feng , Renn Su , April Yi Wang

With increasing digitalization, Artificial Intelligence (AI) is becoming ubiquitous. AI-based systems to identify, optimize, automate, and scale solutions to complex economic and societal problems are being proposed and implemented. This…

Concept-based explainability methods provide insight into deep learning systems by constructing explanations using human-understandable concepts. While the literature on human reasoning demonstrates that we exploit relationships between…

Machine Learning · Computer Science 2024-05-29 Naveen Raman , Mateo Espinosa Zarlenga , Mateja Jamnik

Deep learning continues to play as a powerful state-of-art technique that has achieved extraordinary accuracy levels in various domains of regression and classification tasks, including images, video, signal, and natural language data. The…

Neural and Evolutionary Computing · Computer Science 2022-06-03 Anna Zou , Zhiyuan Li

In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in…

Human-Computer Interaction · Computer Science 2025-03-13 Shuai Ma , Qiaoyi Chen , Xinru Wang , Chengbo Zheng , Zhenhui Peng , Ming Yin , Xiaojuan Ma

A fascinating hypothesis is that human and animal intelligence could be explained by a few principles (rather than an encyclopedic list of heuristics). If that hypothesis was correct, we could more easily both understand our own…

Machine Learning · Computer Science 2022-08-02 Anirudh Goyal , Yoshua Bengio

Intelligence can be defined as a predominantly human ability to accomplish tasks that are generally hard for computers and animals. Artificial Intelligence [AI] is a field attempting to accomplish such tasks with computers. AI is becoming…

Artificial Intelligence · Computer Science 2019-05-03 George Cevora

Building trust in AI-based systems is deemed critical for their adoption and appropriate use. Recent research has thus attempted to evaluate how various attributes of these systems affect user trust. However, limitations regarding the…

Human-Computer Interaction · Computer Science 2022-04-29 Michaela Benk , Suzanne Tolmeijer , Florian von Wangenheim , Andrea Ferrario