Related papers: Synthesizing Interpretable Control Policies throug…

Large Language models (LLMs) have shown promise as generators of symbolic control policies, producing interpretable program-like representations through iterative search. However, these models are not capable of separating the functional…

Although the synthesis of programs encoding policies often carries the promise of interpretability, systematic evaluations were never performed to assess the interpretability of these policies, likely because of the complexity of such an…

Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…

Deep reinforcement learning has achieved impressive success in control tasks. However, its policies, represented as opaque neural networks, are often difficult for humans to understand, verify, and debug, which undermines trust and hinders…

Cloud computing is ubiquitous, with a growing number of services being hosted on the cloud every day. Typical cloud compute systems allow administrators to write policies implementing access control rules which specify how access to private…

The trade-off between expressiveness and interpretability remains a core challenge when building human-centric predictive models for classification and decision-making. While symbolic rules offer interpretability, they often lack…

Large language models (LLMs) trained on code completion have been shown to be capable of synthesizing simple Python programs from docstrings [1]. We find that these code-writing LLMs can be re-purposed to write robot policy code, given…

Interpretable machine learning has exploded as an area of interest over the last decade, sparked by the rise of increasingly large datasets and deep neural networks. Simultaneously, large language models (LLMs) have demonstrated remarkable…

This paper introduces an approach to increasing the explainability of artificial intelligence (AI) systems by embedding Large Language Models (LLMs) within standardized analytical processes. While traditional explainable AI (XAI) methods…

As multiple crises threaten the sustainability of our societies and pose at risk the planetary boundaries, complex challenges require timely, updated, and usable information. Natural-language processing (NLP) tools enhance and expand data…

Large language models are a form of artificial intelligence systems whose primary knowledge consists of the statistical patterns, semantic relationships, and syntactical structures of language1. Despite their limited forms of "knowledge",…

Large language models (LLMs) have shown impressive capabilities across a wide range of language tasks. However, their reasoning process is primarily guided by statistical patterns in training data, which limits their ability to handle novel…

Inspired by the exceptional general intelligence of Large Language Models (LLMs), researchers have begun to explore their application in pioneering the next generation of recommender systems - systems that are conversational, explainable,…

We introduce a simple approach that uses a large language model (LLM) to automatically implement a fully interpretable rule-based data-to-text system in pure Python. Experimental evaluation on the WebNLG dataset showed that such a…

This article introduces an innovative architecture designed to declaratively combine Large Language Models (LLMs) with shared histories, and triggers to identify the most appropriate LLM for a given task. Our approach is general and…

We propose a method that enables large language models (LLMs) to control embodied agents through the generation of control policies that directly map continuous observation vectors to continuous action vectors. At the outset, the LLMs…

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

Mechanism design has long been a cornerstone of economic theory, with traditional approaches relying on mathematical derivations. Recently, automated approaches, including differentiable economics with neural networks, have emerged for…

In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically…

We demonstrate the ability of large language models (LLMs) to perform iterative self-improvement of robot policies. An important insight of this paper is that LLMs have a built-in ability to perform (stochastic) numerical optimization and…