Related papers: Implementing Dynamic Programming in Computability …

In this work, we present a simple, uniform, and elegant solution to the problem, with stunning practical effectiveness and application to virtually any Datalog-based analysis. The approach consists of leveraging the choice construct,…

Argumentation problems are concerned with determining the acceptability of a set of arguments from their relational structure. When the available information is uncertain, probabilistic argumentation frameworks provide modelling tools to…

Long chain-of-thought (CoT) is an essential ingredient in effective usage of modern large language models, but our understanding of the reasoning strategies underlying these capabilities remains limited. While some prior works have…

Scientific computing has experienced a surge empowered by advancements in technologies such as neural networks. However, certain important tasks are less amenable to these technologies, benefiting from innovations to traditional inference…

Scaling Visual Question Answering (VQA) to the open-domain and multi-hop nature of web searches, requires fundamental advances in visual representation learning, knowledge aggregation, and language generation. In this work, we introduce…

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability…

Logic programming, as exemplified by datalog, defines the meaning of a program as its unique smallest model: the deductive closure of its inference rules. However, many problems call for an enumeration of models that vary along some set of…

LLM benchmarks are increasingly dynamic: instead of containing a fixed set of questions, they define templates and parameters that can generate an effectively unlimited number of question variants. This flexibility is valuable, but it makes…

Multi-step reasoning ability of large language models is crucial in tasks such as math and tool utilization. Current researches predominantly focus on enhancing model performance in these multi-step reasoning tasks through fine-tuning with…

The rapid adoption of large language models (LLMs) has enabled new forms of AI-assisted reasoning across scientific, technical, and organizational domains. However, prevailing modes of LLM use remain cognitively unstructured: problem…

Mathematical reasoning poses significant challenges for Large Language Models (LLMs) due to its demand for multi-step reasoning and abstract conceptual integration. While recent test-time scaling techniques rely heavily on high-quality,…

Rule-based models are attractive for various tasks because they inherently lead to interpretable and explainable decisions and can easily incorporate prior knowledge. However, such systems are difficult to apply to problems involving…

Engineering system design, viewed as a decision-making process, faces challenges due to complexity and uncertainty. In this paper, we present a framework proposing the use of the Deep Q-learning algorithm to optimize the design of…

Large language models (LLMs) have shown significant general language understanding abilities. However, there has been a scarcity of attempts to assess the logical reasoning capacities of these LLMs, an essential facet of natural language…

This paper presents Holbert: a work-in-progress pedagogical proof assistant and online textbook platform, aimed at the educational use-case, specifically for the teaching of programming language theory. Holbert allows proof exercises and…

Decentralized large language model (LLM) inference promises transparent and censorship resistant access to advanced AI, yet existing verification approaches struggle to scale to modern models. Proof of Quality (PoQ) replaces cryptographic…

While Chain-of-Thought (CoT) prompting enhances the reasoning capabilities of large language models, the faithfulness of the generated rationales remains an open problem for model interpretability. We propose a novel theoretical lens for…

We introduce the lookahead-bounded Q-learning (LBQL) algorithm, a new, provably convergent variant of Q-learning that seeks to improve the performance of standard Q-learning in stochastic environments through the use of ``lookahead'' upper…

The past few years have seen a surge of interest in the field of probabilistic logic learning and statistical relational learning. In this endeavor, many probabilistic logics have been developed. ProbLog is a recent probabilistic extension…

Neural networks have continued to gain prevalence in the modern era for their ability to model complex data through pattern recognition and behavior remodeling. However, the static construction of traditional neural networks inhibits…