English
Related papers

Related papers: A different perspective on a scale for pairwise co…

200 papers

Scalable oversight protocols aim to empower evaluators to accurately verify AI models more capable than themselves. However, human evaluators are subject to biases that can lead to systematic errors. We conduct two studies examining the…

Human-Computer Interaction · Computer Science 2025-07-29 Gabriel Recchia , Chatrik Singh Mangat , Jinu Nyachhyon , Mridul Sharma , Callum Canavan , Dylan Epstein-Gross , Muhammed Abdulbari

We present a technique for estimating the similarity between objects such as movies or foods whose proper representation depends on human perception. Our technique combines a modest number of human similarity assessments to infer a pairwise…

Artificial Intelligence · Computer Science 2018-02-19 Jesse Anderton , Pavel Metrikov , Virgil Pavlu , Javed Aslam

Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit biases in evaluation and often struggle to generate coherent…

Computation and Language · Computer Science 2025-01-20 Yinhong Liu , Han Zhou , Zhijiang Guo , Ehsan Shareghi , Ivan Vulić , Anna Korhonen , Nigel Collier

As large language models (LLMs) are increasingly used as evaluators for natural language generation tasks, ensuring unbiased assessments is essential. However, LLM evaluators often display biased preferences, such as favoring verbosity and…

Computation and Language · Computer Science 2025-04-21 Hawon Jeong , ChaeHun Park , Jimin Hong , Hojoon Lee , Jaegul Choo

Many constructs that characterize language, like its complexity or emotionality, have a naturally continuous semantic structure; a public speech is not just "simple" or "complex," but exists on a continuum between extremes. Although large…

Computation and Language · Computer Science 2025-09-23 Hauke Licht , Rupak Sarkar , Patrick Y. Wu , Pranav Goel , Niklas Stoehr , Elliott Ash , Alexander Miserlis Hoyle

In addition to objective indicators (e.g. laboratory values), clinical data often contain subjective evaluations by experts (e.g. disease severity assessments). While objective indicators are more transparent and robust, the subjective…

In this study, we provide mathematical and practice-driven justification for using $[0,1]$ normalization of inconsistency indicators in pairwise comparisons. The need for normalization, as well as problems with the lack of normalization,…

Discrete Mathematics · Computer Science 2017-02-28 W. W. Koczkodaj , J. -P. Magnot , J. Mazurek , J. F. Peters , H. Rakhshani , M. Soltys , D. Strzałka , J. Szybowski , A. Tozzi

Personalized recommendation attracts a surge of interdisciplinary researches. Especially, similarity based methods in applications of real recommendation systems achieve great success. However, the computations of similarities are…

Information Retrieval · Computer Science 2014-07-30 Xuzhen Zhu , Hui Tian , Shimin Cai

The simple pairwise comparison is a method to provide different criteria with weights. We show that the values of those weights (in particular the maximum) depend just on the number of criteria. Additionally, it is shown that the distance…

Theoretical Economics · Economics 2020-03-25 Stefan Lörcks

An important side effect of the evolution of the human brain is an increased capacity to form opinions in a very large domain of issues, which become points of aggressive interpersonal disputes. Remarkably, such disputes are often no less…

Social and Information Networks · Computer Science 2014-01-14 Noah E. Friedkin

In this paper, we consider large-scale ranking problems where one is given a set of (possibly non-redundant) pairwise comparisons and the underlying ranking explained by those comparisons is desired. We show that stochastic gradient descent…

Optimization and Control · Mathematics 2024-07-04 Benjamin Jarman , Lara Kassab , Deanna Needell , Alexander Sietsema

Comparing clusterings is central to evaluating unsupervised models, yet the many existing similarity measures can produce widely divergent, sometimes contradictory, evaluations. Clustering similarity measures are typically organized into…

Machine Learning · Statistics 2025-11-06 Alexander J. Gates

An observational study may be biased for estimating causal effects by failing to control for unmeasured confounders. This paper proposes a new quantity called the "sensitivity value", which is defined as the minimum strength of unmeasured…

Methodology · Statistics 2017-05-24 Qingyuan Zhao

We introduce two new inconsistency measures for the incomplete pairwise comparisons matrices and show several examples of their calculation. We also carry out a comparative analysis of the new inconsistency indices with the existing ones…

Information Theory · Computer Science 2019-12-09 Jacek Szybowski , Konrad Kułakowski , Anna Prusak

Systematic reviews of interventions are important tools for synthesizing evidence from multiple studies. They serve to increase power and improve precision, in the same way that larger studies can do, but also to establish the consistency…

Methodology · Statistics 2021-04-20 Iman Jaljuli , Yoav Benjamini , Liat Shenhav , Orestis Panagiotou , Ruth Heller

The goal of most subjective studies is to place a set of stimuli on a perceptual scale. This is mostly done directly by rating, e.g. using single or double stimulus methodologies, or indirectly by ranking or pairwise comparison. All these…

Neurons and Cognition · Quantitative Biology 2022-03-25 Pastor Andréas , Lukáš Krasula , Xiaoqing Zhu , Zhi Li , Patrick Le Callet

Current alignment pipelines presume a single, universal notion of desirable behavior. However, human preferences often diverge across users, contexts, and cultures. As a result, disagreement collapses into the majority signal and minority…

Machine Learning · Computer Science 2025-06-10 Daniel Halpern , Evi Micha , Ariel D. Procaccia , Itai Shapira

Chess championships are often organised as a Swiss-system tournament, causing great challenges in ranking the participants due to the different strength of schedules and possible circular triads. The paper suggests that pairwise comparison…

Applications · Statistics 2016-11-03 Lászlo Csató

If two experts disagree on a test, we may conclude both cannot be 100 per cent correct. But if they completely agree, no possible evaluation can be excluded. This asymmetry in the utility of agreements versus disagreements is explored here…

Artificial Intelligence · Computer Science 2025-10-02 Andrés Corrada-Emmanuel

The rapid advancement and widespread adoption of machine learning-driven technologies have underscored the practical and ethical need for creating interpretable artificial intelligence systems. Feature importance, a method that assigns…

Machine Learning · Computer Science 2023-12-07 Nimrod Harel , Uri Obolski , Ran Gilad-Bachrach