English
Related papers

Related papers: When is it Better to Compare than to Score?

200 papers

Modern instruction-tuned models have become highly capable in text generation tasks such as summarization, and are expected to be released at a steady pace. In practice one may now wish to choose confidently, but with minimal effort, the…

Computation and Language · Computer Science 2024-03-01 Chantal Shaib , Joe Barrow , Alexa F. Siu , Byron C. Wallace , Ani Nenkova

Humans know when to reach for help e.g. $347 \times 28$ warrants a calculator while $2+2$ does not. Language models do not. Prompt-based approaches can instruct a model when to invoke tools, but this scaffolding does not teach it to…

Machine Learning · Computer Science 2026-05-28 Abhijit Kumar , Zoey Wu , Mohit Suley

Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we analyze specific properties which make a benchmark more…

Computation and Language · Computer Science 2025-08-19 David Heineman , Valentin Hofmann , Ian Magnusson , Yuling Gu , Noah A. Smith , Hannaneh Hajishirzi , Kyle Lo , Jesse Dodge

We introduce an ordinate method for noisy data analysis, based solely on rank information and thus insensitive to outliers. The method is nonparametric, objective, and the required data processing is parsimonious. Main ingredients are a…

Data Analysis, Statistics and Probability · Physics 2019-09-11 Glenn Ierley , Alex Kostinski

Recommender systems are central to modern online platforms, but a popular concern is that they may be pulling society in dangerous directions (e.g., towards filter bubbles). However, a challenge with measuring the effects of recommender…

Computers and Society · Computer Science 2021-10-25 Serina Chang , Johan Ugander

We consider the problem of maximizing a monotone submodular function under noise. There has been a great deal of work on optimization of submodular functions under various constraints, resulting in algorithms that provide desirable…

Data Structures and Algorithms · Computer Science 2016-11-08 Avinatan Hassidim , Yaron Singer

In many contexts it is extremely costly to perform enough high quality experimental measurements to accurately parameterize a predictive quantitative model. However, it is often much easier to carry out large numbers of experiments that…

Data Analysis, Statistics and Probability · Physics 2017-11-22 Alpha A. Lee , Michael P. Brenner , Lucy J. Colwell

In many problem settings, most notably in game playing, an agent receives a possibly delayed reward for its actions. Often, those rewards are handcrafted and not naturally given. Even simple terminal-only rewards, like winning equals 1 and…

Artificial Intelligence · Computer Science 2020-12-09 Tobias Joppen , Johannes Fürnkranz

Ordinal data are quite common in applied statistics. Although some model selection and regularization techniques for categorical predictors and ordinal response models have been developed over the past few years, less work has been done…

Methodology · Statistics 2024-07-26 Aisouda Hoshiyar , Laura H. Gertheiss , Jan Gertheiss

The question of aggregating pair-wise comparisons to obtain a global ranking over a collection of objects has been of interest for a very long time: be it ranking of online gamers (e.g. MSR's TrueSkill system) and chess players, aggregating…

Machine Learning · Computer Science 2015-11-13 Sahand Negahban , Sewoong Oh , Devavrat Shah

A general many quantiles + noise model is studied in the robust formulation (allowing non-normal, non-independent observations), where the identifiability requirement for the noise is formulated in terms of quantiles rather than the…

Statistics Theory · Mathematics 2022-11-21 Eduard Belitser , Paulo Serra , Alexandra Vegelien

Curriculum Learning is the presentation of samples to the machine learning model in a meaningful order instead of a random order. The main challenge of Curriculum Learning is determining how to rank these samples. The ranking of the samples…

Machine Learning · Computer Science 2022-09-12 H. Toprak Kesgin , M. Fatih Amasyali

Randomised controlled trials aim to assess the impact of one (or more) health interventions relative to other standard interventions. RCTs sometimes use an ordinal outcome, which is an endpoint that comprises of multiple, monotonically…

Methodology · Statistics 2022-08-15 Chris J. Selman , Katherine J. Lee , Robert K. Mahar

LLM confidence calibration is often evaluated by comparing two signals: token-probability scores and verbalized confidence. These signals are sometimes treated as direct readouts of model uncertainty, but their comparison depends on…

Artificial Intelligence · Computer Science 2026-05-28 Hankyeol Kim , Pilsung Kang

To reduce the need for human annotations, large language models (LLMs) have been proposed as judges of the quality of other candidate models. The performance of LLM judges is typically evaluated by measuring the correlation with human…

Computation and Language · Computer Science 2025-05-14 Andreas Stephan , Dawei Zhu , Matthias Aßenmacher , Xiaoyu Shen , Benjamin Roth

This paper studies the problem of finding the exact ranking from noisy comparisons. A comparison over a set of $m$ items produces a noisy outcome about the most preferred item, and reveals some information about the ranking. By repeatedly…

Machine Learning · Computer Science 2021-07-30 Wenbo Ren , Jia Liu , Ness B. Shroff

Making a decision is often a matter of listing and comparing positive and negative arguments. In such cases, the evaluation scale for decisions should be considered bipolar, that is, negative and positive values should be explicitly…

Artificial Intelligence · Computer Science 2014-01-16 Didier Dubois , Hélène Fargier , Jean-François Bonnefon

Recent years have seen growing interest in Question Difficulty Estimation (QDE) using natural language processing techniques. Question difficulty is often represented using discrete levels, framing the task as ordinal regression due to the…

Machine Learning · Computer Science 2025-07-04 Arthur Thuy , Ekaterina Loginova , Dries F. Benoit

We prove that the ordinary least-squares (OLS) estimator attains nearly minimax optimal performance for the identification of linear dynamical systems from a single observed trajectory. Our upper bound relies on a generalization of…

Machine Learning · Computer Science 2018-05-25 Max Simchowitz , Horia Mania , Stephen Tu , Michael I. Jordan , Benjamin Recht

In the field of large language model (LLM)-based proof generation, despite extensive training on large datasets such as ArXiv, LLMs still exhibit only modest performance on proving tasks of moderate difficulty. We believe that this is…