arXiv research

We detect lookahead bias in LLM forecasts using a novel statistical method.

In a seminal paper "Volumen und Oberfläche" (1903), Minkowski introduced the basic notion of mixed volumes and the corresponding inequalities that lie at the heart of convex geometry. The fundamental importance of characterizing the extremals of these inequalities was already emphasized by Minkowski himself, but has to…

New algorithm reduces online learning regret for bounded recall games.

This paper introduces a new method to train normalizing flows using precision-recall divergences.

Solves a long-standing convex geometry problem about mixed volumes.

The study examines how class imbalance affects precision-recall curves.

The study formalizes temporal precision and recall for anomaly detection in sequences.

For information retrieval and binary classification, we show that precision at the top (or precision at k) and recall at the top (or recall at k) are maximised by thresholding the posterior probability of the positive class. This finding is a consequence of a result on constrained minimisation of the cost-sensitive exp…

Unified and extended precision-recall metrics for generative models.

Transformers can store facts efficiently using associative memories.

Recalls intrinsically harmonic forms and open problems.

LLMs can memorize economic data and recall exact values before their training cutoff.

Paper tackles imbalanced binary classification by optimizing precision and recall directly.

In this article we revisit the definition of Precision-Recall (PR) curves for generative models proposed by Sajjadi et al. (arXiv:1806.00035). Rather than providing a scalar for generative quality, PR curves distinguish mode-collapse (poor recall) and bad quality (poor precision). We first generalize their formulation …

RAGuard improves safety in LLMs for offshore wind maintenance.

Paper proposes a human-algorithm approach to reduce medical device recall risk and workload.

Framework for precise recall control in spatial conflation tasks.

A new method for generating replay samples on the fly, optimizing for not forgetting.

Proposes a new tree-based algorithm for class-imbalanced data.

The paper critiques and expands on common evaluation metrics in machine learning.

New findings show tool-augmented models can recall unlimited facts, outperforming purely memorized models.

Paper tackles non-uniform coverage planning for robots.

The optimal ranking score between precision and recall is rarely F1 and can be found using specific methods.

We study the effectiveness of several techniques to personalize end-to-end speech models and improve the recognition of proper names relevant to the user. These techniques differ in the amounts of user effort required to provide supervision, and are evaluated on how they impact speech recognition performance. We propos…

Recalls and refines the concept of algebraically rectifiable curves.

DIAL learns embeddings to maximize recall and accuracy for entity resolution.

Improves interpretability of neural network intermediate layers by making concept activations more robust and effective.

Transformers recall from long distributions with statistical guarantees.

Short sales are regarded as negative purchases in textbook asset pricing theory. In reality, however, the symmetry between purchases and short sales is broken by a variety of costs and risks peculiar to the latter. We formulate an optimal stopping model in which the decision to cover a short position is affected by two…

Despite the tremendous progress in the estimation of generative models, the development of tools for diagnosing their failures and assessing their performance has advanced at a much slower pace. Recent developments have investigated metrics that quantify which parts of the true distribution is modeled well, and, on the…

Enhanced anomaly detection using PRC-RF with autoencoders.

LLMs can be tricked into recalling facts based on context clues.

Typically options with a path dependent payoff, such as Target Accumulation Redemption Note (TARN), are evaluated by a Monte Carlo method. This paper describes a finite difference scheme for pricing a TARN option. Key steps in the proposed scheme involve tracking of multiple one-dimensional finite difference solutions,…

Evaluation often aims to reduce the correctness or error characteristics of a system down to a single number, but that always involves trade-offs. Another way of dealing with this is to quote two numbers, such as Recall and Precision, or Sensitivity and Specificity. But it can also be useful to see more than this, and …

Unified framework for sequence models using test-time regression.

New method detects novel node categories in graphs with distribution shifts.

KATA improves associative recall by optimizing feature maps derived from nonnegative attention weights.

New metrics improve reliability of image generation evaluation.

We analyze a model of learning and belief formation in networks in which agents follow Bayes rule yet they do not recall their history of past observations and cannot reason about how other agents' beliefs are formed. They do so by making rational inferences about their observations which include a sequence of independ…

Study improves detection of cryptocurrency pump-and-dump schemes.

Smooth calibration improves forecast reliability even with leaked information.

This study is motivated by the magnitude of the problem of Louisiana high school dropout and its negative impacts on individual and public well-being. Our goal is to predict students who are at risk of high school dropout, by examining Louisiana administrative dataset. Due to the imbalanced nature of the dataset, imbal…

We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the impo…

Paper introduces a new performance metric for class imbalance datasets.

We address challenges of active learning under scarce informational resources in non-stationary environments. In real-world settings, data labeled and integrated into a predictive model may become invalid over time. However, the data can become informative again with switches in context and such changes may indicate un…

Recall assistance methods are among the key aspects that improve the accuracy of online dietary assessment surveys. These methods still mainly rely on experience of trained interviewers with nutritional background, but data driven approaches could improve cost-efficiency and scalability of automated dietary assessment.…

Batch normalization improves deep networks by aligning their decision boundaries with data.

This encyclopedia article briefly reviews without proofs some of the main results in cotangent bundle reduction. The article recalls most the necessary prerequisites to understand the main results.