English
Related papers

Related papers: Auditing Games for Sandbagging

200 papers

AI systems can fail to learn important behaviors, leading to real-world issues like safety concerns and biases. Discovering these systematic failures often requires significant developer attention, from hypothesizing potential edge cases to…

Human-Computer Interaction · Computer Science 2021-10-28 Ángel Alexander Cabrera , Abraham J. Druck , Jason I. Hong , Adam Perer

As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results while evading detection. We introduce Auditing Sabotage Bench, a benchmark for evaluating…

Artificial Intelligence · Computer Science 2026-04-28 Eric Gan , Aryan Bhatt , Buck Shlegeris , Julian Stastny , Vivek Hebbar

The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for reliable compliance auditing. For binary classifiers,…

Machine Learning · Computer Science 2026-03-10 Valentin Lafargue , Adriana Laurindo Monteiro , Emmanuelle Claeys , Laurent Risser , Jean-Michel Loubes

This paper introduces an information-theoretic method for selecting a subset of problems which gives the most information about a group of problem-solving algorithms. This method was tested on the games in the General Video Game AI (GVGAI)…

Artificial Intelligence · Computer Science 2020-05-19 Matthew Stephenson , Damien Anderson , Ahmed Khalifa , John Levine , Jochen Renz , Julian Togelius , Christoph Salge

Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…

Computation and Language · Computer Science 2020-12-21 Lei Sha , Oana-Maria Camburu , Thomas Lukasiewicz

The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…

Artificial Intelligence · Computer Science 2025-03-11 Dany Moshkovich , Hadar Mulian , Sergey Zeltyn , Natti Eder , Inna Skarbovsky , Roy Abitbol

Fairness and accountability are two essential pillars for trustworthy Artificial Intelligence (AI) in healthcare. However, the existing AI model may be biased in its decision marking. To tackle this issue, we propose an adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-05-12 Xiaoxiao Li , Ziteng Cui , Yifan Wu , Lin Gu , Tatsuya Harada

This paper presents an intelligent and transparent AI-driven system for Credit Risk Assessment using three state-of-the-art ensemble machine learning models combined with Explainable AI (XAI) techniques. The system leverages XGBoost,…

Machine Learning · Computer Science 2025-06-25 Shreya , Harsh Pathak

Although attribute grammars are commonly used for compiler construction, little investigation has been conducted on debugging attribute grammars. The paper proposes two types of systematic debugging methods, an algorithmic debugging and…

Software Engineering · Computer Science 2007-05-23 Yohei Ikezoe , Akira Sasaki , Yoshiki Ohshima , Ken Wakita , Masataka Sassa

As software systems grow increasingly complex, explainability has become a crucial non-functional requirement for transparency, user trust, and regulatory compliance. Eliciting explainability requirements is challenging, as different…

Software Engineering · Computer Science 2025-09-05 Martin Obaidi , Jakob Droste , Hannah Deters , Marc Herrmann , Raymond Ochsner , Jil Klünder , Kurt Schneider

Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model character or personality. Without a clear objective, conventional…

Computation and Language · Computer Science 2025-10-01 Arduin Findeis , Timo Kaufmann , Eyke Hüllermeier , Robert Mullins

The rise of machine learning (ML) is accompanied by several high-profile cases that have stressed the need for fairness, accountability, explainability and trust in ML systems. The existing literature has largely focused on fully automated…

Computers and Society · Computer Science 2023-06-14 Bhavya Ghai

Machine learning models are vulnerable to adversarial inputs that induce seemingly unjustifiable errors. As automated classifiers are increasingly used in industrial control systems and machinery, these adversarial errors could grow to be a…

Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes. Current approaches for solving this problem include model…

Machine Learning · Computer Science 2019-05-16 Ulrich Aïvodji , Hiromi Arai , Olivier Fortineau , Sébastien Gambs , Satoshi Hara , Alain Tapp

We propose a general approach to quantitatively assessing the risk and vulnerability of artificial intelligence (AI) systems to biased decisions. The guiding principle of the proposed approach is that any AI algorithm must outperform a…

Computers and Society · Computer Science 2024-08-13 Shun Ide , Allison Blunt , Djallel Bouneffouf

In AI and law, systems that are designed for decision support should be explainable when pursuing justice. In order for these systems to be fair and responsible, they should make correct decisions and make them using a sound and transparent…

Artificial Intelligence · Computer Science 2021-05-17 Cor Steging , Silja Renooij , Bart Verheij

Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box…

Computation and Language · Computer Science 2020-07-22 Haw-Shiuan Chang , Shankar Vembu , Sunil Mohan , Rheeya Uppaal , Andrew McCallum

The importance of explainability in AI has become a pressing concern, for which several explainable AI (XAI) approaches have been recently proposed. However, most of the available XAI techniques are post-hoc methods, which however may be…

Machine Learning · Computer Science 2022-04-15 Leonardo Lucio Custode , Giovanni Iacca

As artificial intelligence (AI) becomes integral to economy and society, communication gaps between developers, users, and stakeholders hinder trust and informed decision-making. High-level AI labels, inspired by frameworks like EU energy…

Artificial Intelligence · Computer Science 2025-01-22 Raphael Fischer , Magdalena Wischnewski , Alexander van der Staay , Katharina Poitz , Christian Janiesch , Thomas Liebig

While Large Language Models have achieved notable success on formal mathematics benchmarks such as MiniF2F, it remains unclear whether these results stem from genuine logical reasoning or semantic pattern matching against pre-training data.…

Machine Learning · Computer Science 2026-05-04 Lixing Li