English
Related papers

Related papers: A logical alarm for misaligned binary classifiers

200 papers

A binary classifier capable of abstaining from making a label prediction has two goals in tension: minimizing errors, and avoiding abstaining unnecessarily often. In this work, we exactly characterize the best achievable tradeoff between…

Machine Learning · Computer Science 2016-11-30 Akshay Balsubramani

This work considers the problem of binary classification: given training data $x_1, \dots, x_n$ from a certain population, together with associated labels $y_1,\dots, y_n \in \left\{0,1 \right\}$, determine the best label for an element $x$…

Statistics Theory · Mathematics 2016-07-04 Nicolas Garcia Trillos , Ryan Murray

Autonomous software agents operating in dynamic environments need to constantly reason about actions in pursuit of their goals, while taking into consideration norms which might be imposed on those actions. Normative practical reasoning…

Artificial Intelligence · Computer Science 2017-01-31 Zohreh Shams , Marina De Vos , Julian Padget , Wamberto W. Vasconcelos

We introduce a group of related methods for binary classification tasks using probes of the hidden state activations in large language models (LLMs). Performance is on par with the largest and most advanced LLMs currently available, but…

Machine Learning · Computer Science 2024-08-22 John Scoville , Shang Gao , Devanshu Agrawal , Javed Qadrud-Din

Inferring from inconsistency and making decisions are two problems which have always been treated separately by researchers in Artificial Intelligence. Consequently, different models have been proposed for each category. Different…

Artificial Intelligence · Computer Science 2012-07-09 Leila Amgoud

In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many…

Machine Learning · Computer Science 2018-09-26 Akshat Agarwal , Abhinau Kumar , Kyle Dunovan , Erik Peterson , Timothy Verstynen , Katia Sycara

Large language models (LLMs) are increasingly deployed in high-stakes settings where good decisions require forming beliefs over the probability of unknown outcomes. However, it is unclear whether LLMs act as if they hold coherent beliefs…

Artificial Intelligence · Computer Science 2026-05-12 Khurram Yamin , Jingjing Tang , Santiago Cortes-Gomez , Amit Sharma , Eric Horvitz , Bryan Wilder

The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are…

Computation and Language · Computer Science 2025-06-06 Raphaël Millière

Algorithmic fairness literature presents numerous mathematical notions and metrics, and also points to a tradeoff between them while satisficing some or all of them simultaneously. Furthermore, the contextual nature of fairness notions…

Human-Computer Interaction · Computer Science 2022-02-17 Mukund Telukunta , Venkata Sriram Siddhardh Nadendla

As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be…

Computers and Society · Computer Science 2026-03-17 Max Hellrigel-Holderbaum , Edward James Young

In his "ship of state" allegory (\textit{Republic}, Book VI, 488) Plato poses a question -- how can a crew of sailors presumed to know little about the art of navigation recognize the true pilot among them? The allegory argues that a simple…

Artificial Intelligence · Computer Science 2023-12-12 Andrés Corrada-Emmanuel

Verification and validation of agentic behavior have been suggested as important research priorities in efforts to reduce risks associated with the creation of general artificial intelligence (Russell et al 2015). In this paper we question…

Artificial Intelligence · Computer Science 2016-10-12 David J. Jilk

We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The…

Machine Learning · Computer Science 2014-07-15 Chicheng Zhang , Kamalika Chaudhuri

Automated answer matching, which leverages LLMs to evaluate free-text responses by comparing them to a reference answer, shows substantial promise as a scalable and aligned alternative to human evaluation. However, its reliability requires…

Computation and Language · Computer Science 2026-01-15 Manas Khatore , Sumana Sridharan , Kevork Sulahian , Benjamin J. Smith , Shi Feng

Recent years have witnessed a renewed interest in Boolean function in explaining binary classifiers in the field of explainable AI (XAI). The standard approach of Boolean function is propositional logic. We present a modal language of a…

Logic in Computer Science · Computer Science 2023-07-11 Xinghan Liu , Emiliano Lorini

This paper advances the theoretical understanding of active learning label complexity for decision trees as binary classifiers. We make two main contributions. First, we provide the first analysis of the disagreement coefficient for…

LLM-based multi-agent systems can fail even when planned actions are executed correctly because agents may misjudge their knowledge when evaluating plan feasibility, a phenomenon we term epistemic miscalibration in planning. Unlike…

Artificial Intelligence · Computer Science 2026-05-25 Zehao Wang , Shilong Jin , Zhao Cao , Lanjun Wang

The AI alignment problem, which focusses on ensuring that artificial intelligence (AI), including AGI and ASI, systems act according to human values, presents profound challenges. With the progression from narrow AI to Artificial General…

Artificial Intelligence · Computer Science 2025-07-25 Alberto Hernández-Espinosa , Felipe S. Abrahão , Olaf Witkowski , Hector Zenil

The main approach to evaluating communication is by assessing how well it facilitates coordination. If two or more individuals can coordinate through communication, it is generally assumed that they understand one another. We investigate…

Artificial Intelligence · Computer Science 2025-09-30 Nikolaos Kondylidis , Anil Yaman , Frank van Harmelen , Erman Acar , Annette ten Teije

Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense. LLMs might "lie", for example, when instructed to output misinformation. Here, we develop a simple…

Computation and Language · Computer Science 2023-09-28 Lorenzo Pacchiardi , Alex J. Chan , Sören Mindermann , Ilan Moscovitz , Alexa Y. Pan , Yarin Gal , Owain Evans , Jan Brauner