Related papers: Neuro-Symbolic Generation and Validation of Memory…
Feature selection aims to identify the optimal feature subset for enhancing downstream models. Effective feature selection can remove redundant features, save computational resources, accelerate the model learning process, and improve the…
Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative…
We study the generalization abilities of language models when translating natural language into formal specifications with complex semantics. In particular, we fine-tune language models on three datasets consisting of English sentences and…
Artificial intelligence systems have achieved remarkable capability in natural language processing, perception and decision-making tasks. However, their behaviour often remains opaque and difficult to verify, limiting their applicability in…
Analysis tools like abstract interpreters, symbolic execution tools and testing tools usually require a proper context to give useful results when analyzing a particular function. Such a context initializes the function parameters and…
Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot. Prior approaches for this task possess one of the following limitations: (i) rely on…
Generative AI, especially via Large Language Models (LLMs), has transformed content creation across text, images, and music, showcasing capabilities in following instructions through prompting, largely facilitated by instruction tuning.…
Large Language Models (LLMs) execute complex multi-turn interaction protocols but lack formal specifications to verify execution against designer intent. We introduce FASTRIC, a Prompt Specification Language that makes implicit Finite State…
This paper is a brief introduction to our recently initiated project named VERIFAI: Traceability and verification of natural language requirements. The project addresses the challenges in the traceability and verification of formal…
Large language models for code generation increasingly rely on synthetic data, where both problem solutions and verification tests are generated by models. While this enables scalable data creation, it introduces a previously unexplored…
The capabilities of Large Language Models (LLMs) in code generation have been extensively studied, particularly for implementing target functionalities from natural-language descriptions. Alternatively, input-output (I/O) examples provide…
How can we perform computations over natural language representations to solve tasks that require symbolic and numeric reasoning? We propose natural language embedded programs (NLEP) as a unifying framework for addressing math/symbolic…
We consider the problem of automatically verifying programs which manipulate arbitrary data structures. Our specification language is expressive, contains a notion of \emph{separation}, and thus enables a precise specification of…
This paper presents a focused literature survey on the use of large language models (LLM) to assist in writing formal specifications for software. A summary of thirty-five key papers is presented, including examples for specifying programs…
Large Language Models (LLMs) demonstrate impressive capabilities in natural language processing but suffer from inaccuracies and logical inconsistencies known as hallucinations. This compromises their reliability, especially in domains…
Large Language Models (LLMs) have shown human-like reasoning abilities but still struggle with complex logical problems. This paper introduces a novel framework, Logic-LM, which integrates LLMs with symbolic solvers to improve logical…
Neuro-symbolic artificial intelligence aims to combine neural architectures with symbolic approaches that can represent knowledge in a human-interpretable formalism. Continual learning concerns with agents that expand their knowledge over…
LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce unacceptable risks where errors carry legal, financial, or safety consequences. This paper…
Computational models of pragmatic language use have traditionally relied on hand-specified sets of utterances and meanings, limiting their applicability to real-world language use. We propose a neuro-symbolic framework that enhances…
The rise of automated code generation tools, such as large language models (LLMs), has introduced new challenges in ensuring the correctness and efficiency of scientific software, particularly in complex kernels, where numerical stability,…