Related papers: Autoformalizing Natural Language to First-Order Lo…
Signal Temporal Logic (STL) is widely used to specify timed and safety-critical tasks for cyber-physical systems, but writing STL formulas directly is difficult for non-expert users. Natural language (NL) provides a convenient interface,…
Recent Large Language Models (LLMs) have significantly advanced natural language processing and automated decision-making. However, these models still encounter difficulties when performing complex reasoning tasks involving logical…
Despite the wide adoption of Large Language Models (LLM)s, clinical decision support systems face a critical challenge: achieving high predictive accuracy while generating explanations aligned with the predictions. Current approaches suffer…
Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math problems stated in natural language. While Large Language Models…
In this paper we examine the limitations of Large Language Models (LLMs) for complex reasoning tasks. Although recent works have started to employ formal languages as an intermediate representation for reasoning tasks, they often face…
Large language models (LLMs) have exhibited impressive capabilities across a myriad of tasks, yet they occasionally yield undesirable outputs. We posit that these limitations are rooted in the foundational autoregressive architecture of…
Reasoning has been a central topic in artificial intelligence from the beginning. The recent progress made on distributed representation and neural networks continues to improve the state-of-the-art performance of natural language…
Natural Language Processing (NLP) is a key technique for developing Medical Artificial Intelligence (AI) systems that leverage Electronic Health Record (EHR) data to build diagnostic and prognostic models. NLP enables the conversion of…
Natural language is an intuitive way for humans to communicate tasks to a robot. While natural language (NL) is ambiguous, real world tasks and their safety requirements need to be communicated unambiguously. Signal Temporal Logic (STL) is…
We study a synthetic corpus based approach for language models (LMs) to acquire logical deductive reasoning ability. The previous studies generated deduction examples using specific sets of deduction rules. However, these rules were limited…
Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…
Logical fallacies are common in public communication and can mislead audiences; fallacious arguments may still appear convincing despite lacking soundness, because convincingness is inherently subjective. We present the first computational…
Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic framework that combines LLMs with SMT solvers to produce…
Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…
As machine learning becomes more widespread and is used in more critical applications, it's important to provide explanations for these models, to prevent unintended behavior. Unfortunately, many current interpretability methods struggle…
Legal reasoning requires both precise interpretation of statutory language and consistent application of complex rules, presenting significant challenges for AI systems. This paper introduces a modular multi-agent framework that decomposes…
We present the first experiments on Native Language Identification (NLI) using LLMs such as GPT-4. NLI is the task of predicting a writer's first language by analyzing their writings in a second language, and is used in second language…
Formally verifying properties of software code has been a highly desirable task, especially with the emergence of LLM-generated code. In the same vein, they provide an interesting avenue for the exploration of formal verification and…
Previous work in the context of natural language querying of temporal databases has established a method to map automatically from a large subset of English time-related questions to suitable expressions of a temporal logic-like language,…
Natural language explanations represent a proxy for evaluating explanation-based and multi-step Natural Language Inference (NLI) models. However, assessing the validity of explanations for NLI is challenging as it typically involves the…