相关论文: Open Set Authorship Attribution toward Demystifyin…

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

One of the main drivers of the recent advances in authorship verification is the PAN large-scale authorship dataset. Despite generating significant progress in the field, inconsistent performance differences between the closed and open test…

Prior knowledge has been shown very useful to address many natural language processing tasks. Many approaches have been proposed to formalise a variety of knowledge, however, whether the proposed approach is robust or sensitive to the…

We describe a technique for attributing parts of a written text to a set of unknown authors. Nothing is assumed to be known a priori about the writing styles of potential authors. We use multiple independent clusterings of an input text to…

Artificial intelligence and machine learning algorithms have become ubiquitous. Although they offer a wide range of benefits, their adoption in decision-critical fields is limited by their lack of interpretability, particularly with textual…

This article describes a novel approach to chance-constrained programming based on the sample average approximation (SAA) method. Recent work focuses on heuristic approximations to the SAA problem and we introduce a novel approach which…

BERT, as one of the pretrianed language models, attracts the most attention in recent years for creating new benchmarks across GLUE tasks via fine-tuning. One pressing issue is to open up the blackbox and explain the decision makings of…

Data-driven approaches are becoming more common as problem-solving techniques in many areas of research and industry. In most cases, machine learning models are the key component of these solutions, but a solution involves multiple such…

Value alignment is the task of creating autonomous systems whose values align with those of humans. Past work has shown that stories are a potentially rich source of information on human values; however, past work has been limited to…

The rising trend of coauthored academic works obscures the credit assignment that is the basis for decisions of funding and career advancements. In this paper, a simple model based on the assumption of an unvarying "author ability" is…

In many scenarios, the interpretability of machine learning models is a highly required but difficult task. To explain the individual predictions of such models, local model-agnostic approaches have been proposed. However, the process…

We study question-answering over semi-structured data. We introduce a new way to apply the technique of semantic parsing by applying machine learning only to provide annotations that the system infers to be missing; all the other parsing…

Usually, probabilistic automata and probabilistic grammars have crisp symbols as inputs, which can be viewed as the formal models of computing with values. In this paper, we first introduce probabilistic automata and probabilistic grammars…

Effective scientific communication depends on accurate citations that validate sources and guide readers to supporting evidence. Yet academic literature faces mounting challenges: semantic citation errors that misrepresent sources,…

Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). However, the absence of consistent configurations and…

We introduce an increasing-complexity, open-ended, and human-agnostic metric to evaluate foundational and frontier AI models in the context of Artificial General Intelligence (AGI) and Artificial Super Intelligence (ASI) claims. Unlike…

Language models (LMs) are often expected to generate strings in some formal language; for example, structured data, API calls, or code snippets. Although LMs can be tuned to improve their adherence to formal syntax, this does not guarantee…

Weighted Logic is a powerful tool for the specification of calculations over semirings that depend on qualitative information. Using a novel combination of Weighted Logic and Here-and-There (HT) Logic, in which this dependence is based on…

This paper seeks to apply categorical logic to the design of artificial intelligent agents that reason symbolically about objects more richly structured than sets. Using Johnstone's sequent calculus of terms- and formulae-in-context, we…

AIGC tools such as ChatGPT have profoundly changed scientific research, leading to widespread attention on its use on academic writing. Leveraging preprints from large language models, this study examined the use of AIGC in manuscript…