Related papers: A Mimamsa Inspired Framework For Instruction Seque…
As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing accordingly. We argue that a thorough understanding of the instruction itself,…
Despite the tremendous advances that have been made in the last decade on developing useful machine-learning applications, their wider adoption has been hindered by the lack of strong assurance guarantees that can be made about their…
Empowering models to dynamically accomplish tasks specified through natural language instructions represents a promising path toward more capable and general artificial intelligence. In this work, we introduce InstructSeq, an…
We propose a novel type system for verifying that programs correctly implement constant-resource behavior. Our type system extends recent work on automatic amortized resource analysis (AARA), a set of techniques that automatically derive…
Large Language Models demonstrate strong reasoning and generation abilities, yet their behavior in multi-turn tasks often lacks reliability and verifiability. We present a task completion framework that enables LLM-based agents to act under…
In this article, we present a new machine learning model by imitation based on the linguistic description of complex phenomena. The idea consists of, first, capturing the behaviour of human players by creating a computational perception…
Large Language Models (LLMs) have shown considerable potential in automating decision logic within knowledge-intensive processes. However, their effectiveness largely depends on the strategy and quality of prompting. Since decision logic is…
As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable controls. We introduce a regulatory machine learning framework that converts unstructured design…
Chat-based prompts respond with verbose linear-sequential texts, making it difficult to explore and refine ambiguous intents, back up and reinterpret, or shift directions in creative AI-assisted design work. AI-Instruments instead embody…
In this work we introduce a structured signaling game, an extension of the classical signaling game with a similarity structure between meanings in the context, along with a variant of the Rational Speech Act (RSA) framework which we call…
AI-powered planning tools show promise in supporting programming learners by enabling early, formative feedback on their thinking processes prior to coding. To date, however, most AI-supported planning tools rely on students'…
The ability to perform complex tasks from detailed instructions is a key to many remarkable achievements of our species. As humans, we are not only capable of performing a wide variety of tasks but also very complex ones that may entail…
This paper presents a framework for enforcing penalties on intelligent agents that do not comply with authorization or obligation policies in a changing environment. A framework is proposed to represent and reason about penalties in plans,…
Here we build a hierarchical modular network called Language guided machine action (LGMA), whose modules process information stream mimicking human cortical network that allows to achieve multiple general tasks such as language guided…
Ensuring ethical behavior in Artificial Intelligence (AI) systems amidst their increasing ubiquity and influence is a major concern the world over. The use of formal methods in AI ethics is a possible crucial approach for specifying and…
Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency, particularly in real-world scenarios with costly physical interactions. This paper introduces a novel human-inspired framework to…
We propose a novel active learning framework for activity recognition using wearable sensors. Our work is unique in that it takes physical and cognitive limitations of the oracle into account when selecting sensor data to be annotated by…
Rule-based systems remain central in safety-critical domains but often struggle with scalability, brittleness, and goal misspecification. These limitations can lead to reward hacking and failures in formal verification, as AI systems tend…
This article introduces a fully automated verification technique that permits to analyze real-time systems described using a continuous notion of time and a mixture of operational (i.e., automata-based) and descriptive (i.e., logic-based)…
Multi-Agent Reinforcement Learning can lead to the development of collaborative agent behaviors that show similarities with organizational concepts. Pushing forward this perspective, we introduce a novel framework that explicitly…