Related papers: The Power of Word-Frequency Based Alignment-Free F…
Understanding the effect of a feature vector $x \in \mathbb{R}^d$ on the response value (label) $y \in \mathbb{R}$ is the cornerstone of many statistical learning problems. Ideally, it is desired to understand how a set of collected…
AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the…
The lifelong user behavior sequence provides abundant information of user preference and gains impressive improvement in the recommendation task, however increases computational consumption significantly. To meet the severe latency…
Testing restrictions on regression coefficients in linear models often requires correcting the conventional F-test for potential heteroskedasticity or autocorrelation amongst the disturbances, leading to so-called heteroskedasticity and…
Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…
In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via…
The Frequency Following Response (FFR) reflects the brain's neural encoding of auditory stimuli including speech. Because the fundamental frequency (F0), a physical correlate of pitch, is one of the essential features of speech, there has…
While deep learning is a powerful tool for natural language processing (NLP) problems, successful solutions to these problems rely heavily on large amounts of annotated samples. However, manually annotating data is expensive and…
In this paper we exploit concepts of information theory to address the fundamental problem of identifying and defining the most suitable tools to extract, in a automatic and agnostic way, information from a generic string of characters. We…
This paper develops a framework for testing for associations in a possibly high-dimensional linear model where the number of features/variables may far exceed the number of observational units. In this framework, the observations are split…
Scale-free networks play a fundamental role in the study of complex networks and various applied fields due to their ability to model a wide range of real-world systems. A key characteristic of these networks is their degree distribution,…
The costly human effort required to prepare the training data of machine learning (ML) models hinders their practical development and usage in software engineering (ML4Code), especially for those with limited budgets. Therefore, efficiently…
Background: Sequence comparison is essential in bioinformatics, serving various purposes such as taxonomy, functional inference, and drug discovery. The traditional method of aligning sequences for comparison is time-consuming, especially…
Large language models (LLMs) have shown the emergent capability of in-context learning (ICL). One line of research has claimed that ICL is functionally equivalent to gradient descent, a type of error-driven learning mechanism. In this…
Large language models (LLMs) are increasingly deployed not only to make decisions but to explain them. While AI decision fairness has been studied extensively, the fairness of AI explanations (whether LLMs justify decisions with equal…
In a case-control study aimed at locating autosomal disease variants for a disease of interest, association between markers and the disease status is often tested by comparing the marker minor allele frequencies (MAFs) between cases and…
The paper considers various formalisms based on Automata, Temporal Logic and Regular Expressions for specifying queries over sequences. Unlike traditional binary semantics, the paper presents a similarity based semantics for thse…
Our research proposes a novel method for reducing the dimensionality of functional data, specifically for the case where the response is a scalar and the predictor is a random function. Our method utilizes distance covariance, and has…
Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not…
Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry. To satisfy the millisecond-level response requirements of online systems while retaining the…