相关论文: Lash 1.0 (System Description)

Text analysis of tabular data relies on two core operations: \emph{summarization} for corpus-level theme extraction and \emph{tagging} for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks…

B-Prolog is a high-performance implementation of the standard Prolog language with several extensions including matching clauses, action rules for event handling, finite-domain constraint solving, arrays and hash tables, declarative loop…

The task of linearization is to find a grammatical order given a set of words. Traditional models use statistical methods. Syntactic linearization systems, which generate a sentence along with its syntactic tree, have shown state-of-the-art…

Many complex scenarios require the coordination of agents possessing unique points of view and distinct semantic commitments. In response, standpoint logic (SL) was introduced in the context of knowledge integration, allowing one to reason…

We introduce LAM, a subsystem of IMALL2 with restricted additive rules able to manage duplication linearly, called linear additive rules. LAM is presented as the type assignment system for a calculus endowed with copy constructors, which…

Noting that lemmas are a key feature of mathematics, we engage in an investigation of the role of lemmas in automated theorem proving. The paper describes experiments with a combined system involving learning technology that generates…

We introduce Deep Adaptive Semantic Logic (DASL), a novel framework for automating the generation of deep neural networks that incorporates user-provided formal knowledge to improve learning from data. We provide formal semantics that…

Rascal is a high-level transformation language that aims to simplify software language engineering tasks like defining program syntax, analyzing and transforming programs, and performing code generation. The language provides several…

The overall goal of this paper is to investigate the theoretical foundations of algorithmic verification techniques for first order linear logic specifications. The fragment of linear logic we consider in this paper is based on the linear…

Spoken language assessment (SLA) systems restrict themselves to evaluating the pronunciation and oral fluency of a speaker by analysing the read and spontaneous spoken utterances respectively. The assessment of language grammar or…

Reinforcement learning (RL) has emerged as the de-facto paradigm for improving the reasoning capabilities of large language models (LLMs). We have developed RLAX, a scalable RL framework on TPUs. RLAX employs a parameter-server…

Lexical Substitution discovers appropriate substitutes for a given target word in a context sentence. However, the task fails to consider substitutes that are of equal or higher proficiency than the target, an aspect that could be…

Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems that poorly align…

The RISC Algorithm Language (RISCAL) is a language for the formal modeling of theories and algorithms. A RISCAL specification describes an infinite class of models each of which has finite size; this allows to fully automatically check in…

Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty quantification and model selection. The Laplace approximation…

The problem-solving in automated theorem proving (ATP) can be interpreted as a search problem where the prover constructs a proof tree step by step. In this paper, we propose a deep reinforcement learning algorithm for proof search in…

We introduce a lazy approach to the explanation-based approximation of probabilistic logic programs. It uses only the most significant part of the program when searching for explanations. The result is a fast and anytime approximate…

Natural Language-conditioned reinforcement learning (RL) enables the agents to follow human instructions. Previous approaches generally implemented language-conditioned RL by providing human instructions in natural language (NL) and…

Automated machine learning makes it easier for data scientists to develop pipelines by searching over possible choices for hyperparameters, algorithms, and even pipeline topologies. Unfortunately, the syntax for automated machine learning…

Large Language Models (LLMs) excel in text classification, but their complexity hinders interpretability, making it difficult to understand the reasoning behind their predictions. Explainable AI (XAI) methods like LIME and SHAP offer local…