English
Related papers

Related papers: Robustness to fundamental uncertainty in AGI align…

200 papers

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

Multi-group agnostic learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses recent practical concerns such as subgroup fairness and hidden…

Machine Learning · Computer Science 2024-06-18 Christopher Tosh , Daniel Hsu

Multiple Instance Learning (MIL) is a sub-domain of classification problems with positive and negative labels and a "bag" of inputs, where the label is positive if and only if a positive element is contained within the bag, and otherwise is…

Machine Learning · Statistics 2023-10-30 Edward Raff , James Holt

This paper introduces Admissibility Alignment: a reframing of AI alignment as a property of admissible action and decision selection over distributions of outcomes under uncertainty, evaluated through the behavior of candidate policies. We…

Artificial Intelligence · Computer Science 2026-01-06 Chris Duffey

Automated short-answer grading (ASAG) remains a challenging task due to the linguistic variability of student responses and the need for nuanced, rubric-aligned partial credit. While Large Language Models (LLMs) offer a promising solution,…

Computation and Language · Computer Science 2026-01-15 Haotian Deng , Chris Farber , Jiyoon Lee , David Tang

Value alignment problems arise in scenarios where the specified objectives of an AI agent don't match the true underlying objective of its users. The problem has been widely argued to be one of the central safety problems in AI.…

Artificial Intelligence · Computer Science 2023-02-10 Malek Mechergui , Sarath Sreedharan

The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human. Despite tremendous success in the AI research, most of existing methods have only single-cognitive ability. To overcome this limitation…

Artificial Intelligence · Computer Science 2022-06-09 Nanyi Fei , Zhiwu Lu , Yizhao Gao , Guoxing Yang , Yuqi Huo , Jingyuan Wen , Haoyu Lu , Ruihua Song , Xin Gao , Tao Xiang , Hao Sun , Ji-Rong Wen

Recent advances in deep learning have shown that uncertainty estimation is becoming increasingly important in applications such as medical imaging, natural language processing, and autonomous systems. However, accurately quantifying…

Machine Learning · Computer Science 2023-07-04 Uddeshya Upadhyay , Jae Myung Kim , Cordelia Schmidt , Bernhard Schölkopf , Zeynep Akata

To ensure trust in AI models, it is becoming increasingly apparent that evaluation of models must be extended beyond traditional performance metrics, like accuracy, to other dimensions, such as fairness, explainability, adversarial…

Machine Learning · Computer Science 2021-10-01 Moninder Singh , Gevorg Ghalachyan , Kush R. Varshney , Reginald E. Bryant

Despite their broad applicability, transformer-based models still fall short in System~2 reasoning, lacking the generality and adaptivity needed for human--AI alignment. We examine weaknesses on ARC-AGI tasks, revealing gaps in…

Artificial Intelligence · Computer Science 2025-08-14 Sejin Kim , Sundong Kim

We propose the creation of a systematic effort to identify and replicate key findings in neuropsychology and allied fields related to understanding human values. Our aim is to ensure that research underpinning the value alignment problem of…

Artificial Intelligence · Computer Science 2018-09-11 Gopal P. Sarma , Nick J. Hay , Adam Safron

The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discussions of these ideas and suggest this stems from the…

Machine Learning · Computer Science 2025-08-19 Freddie Bickford Smith , Jannik Kossen , Eleanor Trollope , Mark van der Wilk , Adam Foster , Tom Rainforth

Aleatoric uncertainty is an intrinsic property of ill-posed inverse and imaging problems. Its quantification is vital for assessing the reliability of relevant point estimates. In this paper, we propose an efficient framework for…

Image and Video Processing · Electrical Eng. & Systems 2020-01-16 Chen Zhang , Bangti Jin

Multimodal models play a key role in empathy detection, but their performance can suffer when modalities provide conflicting cues. To understand these failures, we examine cases where unimodal and multimodal predictions diverge. Using…

Computation and Language · Computer Science 2025-11-12 Maya Srikanth , Run Chen , Julia Hirschberg

Recent reports of large language models (LLMs) exhibiting behaviors such as deception, threats, or blackmail are often interpreted as evidence of alignment failure or emergent malign agency. We argue that this interpretation rests on a…

Artificial Intelligence · Computer Science 2026-01-14 Didier Sornette , Sandro Claudio Lera , Ke Wu

Starting from considerations about meaning and subsequent use of asymmetric uncertainty intervals of experimental results, we review the issue of uncertainty propagation. We show that, using a probabilistic approach (the so-called Bayesian…

High Energy Physics - Experiment · Physics 2007-05-23 G. D'Agostini , M. Raso

Asymmetric statistical errors arise for experimental results obtained by Maximum Likelihood estimation, in cases where the number of results is finite and the log likelihood function is not a symmetric parabola. This note discusses how…

Data Analysis, Statistics and Probability · Physics 2007-05-23 Roger Barlow

Adaptive robust optimization (ARO) extends static robust optimization by allowing decisions to depend on the realized uncertainty - weakly dominating static solutions within the modeled uncertainty set. However, ARO makes previous…

Optimization and Control · Mathematics 2025-11-20 Karl Zhu , Dimitris Bertsimas

A fundamental problem in robust learning is asymmetry: a learner needs to correctly classify every one of exponentially-many perturbations that an adversary might make to a test-time natural example. In contrast, the attacker only needs to…

Machine Learning · Computer Science 2024-02-14 Saba Ahmadi , Avrim Blum , Omar Montasser , Kevin Stangl

Quantifying uncertainty in clinical predictions is critical for high-stakes diagnosis tasks. Conformal prediction offers a principled approach by providing prediction sets with theoretical coverage guarantees. However, in practice, patient…

Machine Learning · Computer Science 2026-05-01 Arjun Chatterjee , Sayeed Sajjad Razin , John Wu , Siddhartha Laghuvarapu , Jathurshan Pradeepkumar , Jimeng Sun
‹ Prev 1 3 4 5 6 7 10 Next ›