English
Related papers

Related papers: Circumventing interpretability: How to defeat mind…

200 papers

With state-of-the-art models achieving high performance on standard benchmarks, contemporary research paradigms continue to emphasize general intelligence as an enduring objective. However, this pursuit overlooks the fundamental disparities…

Artificial Intelligence · Computer Science 2023-10-03 Nick DiSanto

As AI adoption expands across human society, the problem of aligning AI models to match human preferences remains a grand challenge. Currently, the AI alignment field is deeply divided between behavioral and representational approaches,…

Computers and Society · Computer Science 2025-08-12 Ben Y. Reis , William La Cava

Artificial Intelligence (AI) is rapidly integrating into various aspects of our daily lives, influencing decision-making processes in areas such as targeted advertising and matchmaking algorithms. As AI systems become increasingly…

Artificial Intelligence · Computer Science 2025-03-11 Md. Tanzib Hosain , Mehedi Hasan Anik , Sadman Rafi , Rana Tabassum , Khaleque Insia , Md. Mehrab Siddiky

The field of AI alignment aims to steer AI systems toward human goals, preferences, and ethical principles. Its contributions have been instrumental for improving the output quality, safety, and trustworthiness of today's AI models. This…

Artificial Intelligence · Computer Science 2024-11-26 Robert West , Roland Aydin

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

Computation and Language · Computer Science 2026-02-13 Usman Naseem

This book-length article combines several peer reviewed papers and new material to analyze the issues of ethical artificial intelligence (AI). The behavior of future AI systems can be described by mathematical equations, which are adapted…

Artificial Intelligence · Computer Science 2015-11-18 Bill Hibbard

The young field of AI Safety is still in the process of identifying its challenges and limitations. In this paper, we formally describe one such impossibility result, namely Unpredictability of AI. We prove that it is impossible to…

Artificial Intelligence · Computer Science 2019-05-31 Roman V. Yampolskiy

Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverage large language models (LLMs) at increasing levels of…

Artificial Intelligence · Computer Science 2026-03-23 Tal Haklay , Nikhil Prakash , Sana Pandey , Antonio Torralba , Aaron Mueller , Jacob Andreas , Tamar Rott Shaham , Yonatan Belinkov

Neural networks organize information according to the hierarchical, multi-scale structure of natural data. Methods to interpret model internals should be similarly scale-aware, explicitly tracking how features compose across resolutions and…

Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…

Artificial Intelligence · Computer Science 2026-05-18 Shutong Fan , Lan Zhang , Xiaoyong Yuan

Artificial intelligence (AI) has huge potential to improve the health and well-being of people, but adoption in clinical practice is still limited. Lack of transparency is identified as one of the main barriers to implementation, as…

Artificial Intelligence · Computer Science 2021-01-06 Aniek F. Markus , Jan A. Kors , Peter R. Rijnbeek

Artificial Intelligence (AI) has a tremendous impact on the unexpected growth of technology in almost every aspect. AI-powered systems are monitoring and deciding about sensitive economic and societal issues. The future is towards…

Machine Learning · Computer Science 2022-06-14 Ioannis Mollas , Nick Bassiliades , Grigorios Tsoumakas

When making decisions, people often overlook critical information or are overly swayed by irrelevant information. A common approach to mitigate these biases is to provide decision-makers, especially professionals such as medical doctors,…

Machine Learning · Computer Science 2021-04-13 Julian Skirzyński , Frederic Becker , Falk Lieder

Many hyper-personalized AI systems profile people's characteristics (e.g., personality traits) to provide personalized recommendations. These systems are increasingly used to facilitate interactions among people, such as providing teammate…

Human-Computer Interaction · Computer Science 2024-05-28 Qiaosi Wang , Chidimma L. Anyi , Vedant Das Swain , Ashok K. Goel

With the long term accumulation of high quality educational data, artificial intelligence has shown excellent performance in knowledge tracing. However, due to the lack of interpretability and transparency of some algorithms, this approach…

Computation and Language · Computer Science 2024-03-13 Yanhong Bai , Jiabao Zhao , Tingjiang Wei , Qing Cai , Liang He

Artificial Intelligence (AI) and its data-centric branch of machine learning (ML) have greatly evolved over the last few decades. However, as AI is used increasingly in real world use cases, the importance of the interpretability of and…

Machine Learning · Computer Science 2022-12-01 N. Ranasinghe , A. Ramanan , S. Fernando , P. N. Hameed , D. Herath , T. Malepathirana , P. Suganthan , M. Niranjan , S. Halgamuge

Assessments of algorithmic bias in large language models (LLMs) are generally catered to uncovering systemic discrimination based on protected characteristics such as sex and ethnicity. However, there are over 180 documented cognitive…

Human-Computer Interaction · Computer Science 2023-08-30 Alaina N. Talboy , Elizabeth Fuller

We consider two fundamental and related issues currently faced by Artificial Intelligence (AI) development: the lack of ethics and interpretability of AI decisions. Can interpretable AI decisions help to address ethics in AI? Using a…

Artificial Intelligence · Computer Science 2021-09-21 Jean-Marie John-Mathews

It has become commonplace to assert that autonomous agents will have to be built to follow human rules of behavior--social norms and laws. But human laws and norms are complex and culturally varied systems, in many cases agents will have to…

Artificial Intelligence · Computer Science 2018-11-06 Dylan Hadfield-Menell , McKane Andrus , Gillian K. Hadfield

Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user…

Machine Learning · Statistics 2016-06-20 Marco Tulio Ribeiro , Sameer Singh , Carlos Guestrin