Related papers: Reimplementation and Reinterpretation of the Copyc…
In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as…
Large language models are increasingly solving tasks that are commonly believed to require human-level reasoning ability. However, these models still perform very poorly on benchmarks of general intelligence such as the Abstraction and…
Recently, deep architectures, such as recurrent and recursive neural networks have been successfully applied to various natural language processing tasks. Inspired by bidirectional recurrent neural networks which use representations that…
We present a new approach to enhancing Answer Set Programming (ASP) with Constraint Processing techniques which allows for solving interesting Constraint Satisfaction Problems in ASP. We show how constraints on finite domains can be…
Entity resolution (record linkage, microclustering) systems are notoriously difficult to evaluate. Looking for a needle in a haystack, traditional evaluation methods use sophisticated, application-specific sampling schemes to find matching…
Assessing the degree of similarity of code fragments is crucial for ensuring software quality, but it remains challenging due to the need to capture the deeper semantic aspects of code. Traditional syntactic methods often fail to identify…
Developers often refactor source code to improve its quality during software development. A challenge in refactoring is to determine if it can be applied or not. To help with this decision-making process, we aim to search for past…
Abstract argumentation framework (\AFname) is a unifying framework able to encompass a variety of nonmonotonic reasoning approaches, logic programming and computational argumentation. Yet, efficient approaches for most of the decision and…
Establishing a docker-based replicability infrastructure offers the community a great opportunity: measuring the run time of information retrieval systems. The time required to present query results to a user is paramount to the users…
OpenAI's recent introduction of Reinforcement Fine-Tuning (RFT) showcases the potential of reasoning foundation model and offers a new paradigm for fine-tuning beyond simple pattern imitation. This technical report presents \emph{OpenRFT},…
In this paper, we present three contributions to the field of academic publishing. Firstly, we introduce Lakat, a novel base layer for a publishing system that fosters collaboration, pluralism and permissionless participation. Drawing…
Explicit software architecture models are essential artifacts for communicating, analyzing, and evolving complex software-intensive systems. In ROS~2-based robotic systems, however, structural (de-)composition and integration semantics are…
Studies show that neural networks, not unlike traditional programs, are subject to bugs, e.g., adversarial samples that cause classification errors and discriminatory instances that demonstrate the lack of fairness. Given that neural…
Deep neural networks that yield human interpretable decisions by architectural design have lately become an increasingly popular alternative to post hoc interpretation of traditional black-box models. Among these networks, the arguably most…
We address an important problem in sequence-to-sequence (Seq2Seq) learning referred to as copying, in which certain segments in the input sequence are selectively replicated in the output sequence. A similar phenomenon is observable in…
Architectures that implement the Common Model of Cognition - Soar, ACT-R, and Sigma - have a prominent place in research on cognitive modeling as well as on designing complex intelligent agents. In this paper, we explore how computational…
This study began with a research project, called DISCvR, conducted at the IBM-ILLINOIS Center for Cognitive Computing Systems Reseach. The goal of DISCvR was to build a practical NLP based AI pipeline for document understanding which will…
We propose an autoregressive entity linking model, that is trained with two auxiliary tasks, and learns to re-rank generated samples at inference time. Our proposed novelties address two weaknesses in the literature. First, a recent method…
The disconnect between distributed software artifacts and their supposed source code enables attackers to leverage the build process for inserting malicious functionality. Past research in this field focuses on compiled language ecosystems,…
The microservice architectural style has many advantages such as scalability, reusability, and easy maintainability. Microservices have therefore become a popular architectural choice when developing new applications. Reaping these benefits…