Leandojo: Theorem proving with retrieval-augmented language models
Large language models (LLMs) have shown promise in proving formal theorems using proof
assistants such as Lean. However, existing methods are difficult to reproduce or build on …
assistants such as Lean. However, existing methods are difficult to reproduce or build on …
[HTML][HTML] nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Models
A rigorous formalization of desired system requirements is indispensable when performing
any verification task. This often limits the application of verification techniques, as writing …
any verification task. This often limits the application of verification techniques, as writing …
LINC: A neurosymbolic approach for logical reasoning by combining language models with first-order logic provers
Logical reasoning, ie, deductively inferring the truth value of a conclusion from a set of
premises, is an important task for artificial intelligence with wide potential impacts on …
premises, is an important task for artificial intelligence with wide potential impacts on …
Data-efficient learning of natural language to linear temporal logic translators for robot task specification
To make robots accessible to a broad audience, it is critical to endow them with the ability to
take universal modes of communication, like commands given in natural language, and …
take universal modes of communication, like commands given in natural language, and …
NL2LTL–a python package for converting natural language (NL) instructions to linear temporal logic (LTL) formulas
F Fuggitti, T Chakraborti - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
This is a demonstration of our newly released Python package NL2LTL which leverages the
latest in natural language understanding (NLU) and large language models (LLMs) to …
latest in natural language understanding (NLU) and large language models (LLMs) to …
Learning to follow instructions in text-based games
Text-based games present a unique class of sequential decision making problem in which
agents interact with a partially observable, simulated environment via actions and …
agents interact with a partially observable, simulated environment via actions and …
Harnessing the power of large language models for natural language to first-order logic translation
Translating natural language sentences to first-order logic (NL-FOL translation) is a
longstanding challenge in the NLP and formal logic literature. This paper introduces …
longstanding challenge in the NLP and formal logic literature. This paper introduces …
Towards improving verification productivity with circuit-aware translation of natural language to systemverilog assertions
Assertion-based verification is a technique to ensure that a circuit design conforms to its
specification and help detect errors early in the design process. It is enabled by powerful …
specification and help detect errors early in the design process. It is enabled by powerful …
Towards a mathematics formalisation assistant using large language models
Mathematics formalisation is the task of writing mathematics (ie, definitions, theorem
statements, proofs) in natural language, as found in books and papers, into a formal …
statements, proofs) in natural language, as found in books and papers, into a formal …
Fine-tuning language models using formal methods feedback
Although pre-trained language models encode generic knowledge beneficial for planning
and control, they may fail to generate appropriate control policies for domain-specific tasks …
and control, they may fail to generate appropriate control policies for domain-specific tasks …