English
Related papers

Related papers: A logical alarm for misaligned binary classifiers

200 papers

A formalized and quantifiable responsibility score is a crucial component in many aspects of the development and application of multi-agent systems and autonomous agents. We can employ it to inform decision making processes based on ethical…

Computer Science and Game Theory · Computer Science 2022-09-16 Sarah Hiller , Jonas Israel , Jobst Heitzig

Automated decision support systems promise to help human experts solve multiclass classification tasks more efficiently and accurately. However, existing systems typically require experts to understand when to cede agency to the system or…

Machine Learning · Computer Science 2023-07-03 Eleni Straitouri , Lequn Wang , Nastaran Okati , Manuel Gomez Rodriguez

Calibration is a popular framework to evaluate whether a classifier knows when it does not know - i.e., its predictive probabilities are a good indication of how likely a prediction is to be correct. Correctness is commonly estimated…

Computation and Language · Computer Science 2022-12-01 Joris Baan , Wilker Aziz , Barbara Plank , Raquel Fernández

Assessing uncertainty is an important step towards ensuring the safety and reliability of machine learning systems. Existing uncertainty estimation techniques may fail when their modeling assumptions are not met, e.g. when the data…

Machine Learning · Computer Science 2017-01-24 Volodymyr Kuleshov , Stefano Ermon

As humans interact with autonomous agents to perform increasingly complicated, potentially risky tasks, it is important to be able to efficiently evaluate an agent's performance and correctness. In this paper we formalize and theoretically…

Machine Learning · Computer Science 2021-06-14 Daniel S. Brown , Jordan Schneider , Anca D. Dragan , Scott Niekum

Describing observations or objects in non-mathematical disciplines can often be accomplished by answering a list of questions. These questions can be formulated in such a way that the only possible answers always are ``yes'' or ``no''. This…

Commutative Algebra · Mathematics 2022-07-08 Marcus Weber , Oguzhan Yürük

Minimizing negative impacts of Artificial Intelligent (AI) systems on human societies without human supervision requires them to be able to align with human values. However, most current work only addresses this issue from a technical point…

Computation and Language · Computer Science 2024-08-13 Mehdi Khamassi , Marceau Nahon , Raja Chatila

Reasoning is central to human intelligence. However, fallacious arguments are common, and some exacerbate problems such as spreading misinformation about climate change. In this paper, we propose the task of logical fallacy detection, and…

Computation and Language · Computer Science 2022-12-13 Zhijing Jin , Abhinav Lalwani , Tejas Vaidhya , Xiaoyu Shen , Yiwen Ding , Zhiheng Lyu , Mrinmaya Sachan , Rada Mihalcea , Bernhard Schölkopf

Inconsistencies are ubiquitous in law, administration, and jurisprudence. Though a cure is too much to hope for, we propose a technological remedy. Large language models (LLMs) can accurately extract propositions from arguments and compile…

Computers and Society · Computer Science 2025-09-24 Steve Huntsman

This study empirically validates automated logical specification methods for behavioural models, focusing on their robustness, scalability, and reproducibility. By the systematic reproduction and extension of prior results, we confirm key…

Software Engineering · Computer Science 2025-05-26 Radoslaw Klimek , Jakub Semczyszyn

Large Language Models (LLMs) are increasingly used in tasks such as psychological text analysis and decision-making in automated workflows. However, their reliability remains a concern due to potential biases inherited from their training…

Computation and Language · Computer Science 2025-04-29 Yi-Long Lu , Chunhui Zhang , Wei Wang

Large reasoning models (LRMs) have shown remarkable progress on complex reasoning tasks. However, some questions posed to LRMs are inherently unanswerable, such as math problems lacking sufficient conditions. We find that LRMs continually…

Artificial Intelligence · Computer Science 2026-01-21 Yi Liu , Xiangyu Liu , Zequn Sun , Wei Hu

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…

Computation and Language · Computer Science 2026-02-11 Bakhtawar Ahtisham , Kirk Vanacore , Zhuqian Zhou , Jinsook Lee , Rene F. Kizilcec

The cost of error in many high-stakes settings is asymmetric: misdiagnosing pneumonia when absent is an inconvenience, but failing to detect it when present can be life-threatening. Because of this, artificial intelligence (AI) models used…

General Economics · Economics 2025-11-12 David Autor , Andrew Caplin , Daniel Martin , Philip Marx

Following the rapid increase in Artificial Intelligence (AI) capabilities in recent years, the AI community has voiced concerns regarding possible safety risks. To support decision-making on the safe use and development of AI systems, there…

Machine Learning · Computer Science 2025-04-01 Gil Gekker , Meirav Segal , Dan Lahav , Omer Nevo

AI systems are increasingly deployed in high-stakes contexts (medical diagnosis, legal research, financial analysis) under the assumption they can be governed by norms. This paper demonstrates that the assumption is formally invalid for…

Artificial Intelligence · Computer Science 2026-03-03 Radha Sarma

Large language models (LLMs) are increasingly used for program verification, and yet little is known about \emph{how} they reason about program semantics during this process. In this work, we focus on abstract interpretation based-reasoning…

Machine Learning · Computer Science 2025-10-01 Jacqueline L. Mitchell , Brian Hyeongseok Kim , Chenyu Zhou , Chao Wang

In most classification tasks there are observations that are ambiguous and therefore difficult to correctly label. Set-valued classifiers output sets of plausible labels rather than a single label, thereby giving a more appropriate and…

Methodology · Statistics 2018-12-27 Mauricio Sadinle , Jing Lei , Larry Wasserman

We extend the two-variable logic on data words with guarded regular binary predicates of the form $\widetilde{L}(x,y)$ that is true if positions $x$ and $y$ are in the same class and the factor strictly between $x$ and $y$ is in the regular…

Logic in Computer Science · Computer Science 2026-05-12 Shibashis Guha , Amaldev Manuel , S P Rishal

Artificially intelligent agents deployed in the real-world will require the ability to reliably \textit{cooperate} with humans (as well as other, heterogeneous AI agents). To provide formal guarantees of successful cooperation, we must make…

Machine Learning · Computer Science 2024-07-02 Robert Loftin , Saptarashmi Bandyopadhyay , Mustafa Mert Çelikok