Related papers: Instruction sequences with dynamically instantiate…
This work continues the development of an intensional approach to computability initiated in previous work, in which programs and computations, rather than functions, constitute the primary objects of study. In this setting, models of…
Recent advances in large language models have demonstrated promising capabilities in following simple instructions through instruction tuning. However, real-world tasks often involve complex, multi-step instructions that remain challenging…
This paper describes an alignment-based model for interpreting natural language instructions in context. We approach instruction following as a search over plans, scoring sequences of actions conditioned on structured observations of text…
Test suites assess natural language processing models' performance on specific functionalities: cases of interest involving model robustness, fairness, or particular linguistic capabilities. This paper introduces specification instructions:…
Promises, impositions, proposals, predictions, and suggestions are categorized as voluntary co-operational methods. The class of voluntary co-operational methods is included in the class of so-called directionals. Directionals are…
Multiple supervised learning scenarios are composed by a sequence of classification tasks. For instance, multi-task learning and continual learning aim to learn a sequence of tasks that is either fixed or grows over time. Existing…
Single-pass instruction sequences under execution are considered to produce behaviours to be controlled by some execution environment. Threads as considered in thread algebra model such behaviours: upon each action performed by a thread, a…
Many real-world dynamic systems, both natural and artificial, are understood to be performing computations. For artificial dynamic systems, explicitly designed to perform computation - such as digital computers - by construction, we can…
The goal of inductive logic programming is to induce a logic program (a set of logical rules) that generalises training examples. Inducing programs with many rules and literals is a major challenge. To tackle this challenge, we introduce an…
We study a collaborative scenario where a user not only instructs a system to complete tasks, but also acts alongside it. This allows the user to adapt to the system abilities by changing their language or deciding to simply accomplish some…
Why should computers interpret language incrementally? In recent years psycholinguistic evidence for incremental interpretation has become more and more compelling, suggesting that humans perform semantic interpretation before constituent…
User-driven applications are the programs, in which the full control is given to the users. Designers of such programs are responsible only for developing an instrument for solving some task, but they do not enforce users to work with this…
Memory refinements are designed below to detect those sequences of actions that have been repeated a given number n. Subsequently such sequences are permitted to run without CPU involvement. This mimics human learning. Actions are rehearsed…
Computer programming initially required humans to directly translate their goals into machine code. These goals could have easily been expressed as a written (or human) language directive. Computers, however, had no capacity to…
As the number of robots in our daily surroundings like home, office, restaurants, factory floors, etc. are increasing rapidly, the development of natural human-robot interaction mechanism becomes more vital as it dictates the usability and…
We present Executable Abstract Programs and analyse their role for software development and documentation. The intuitive understanding of these programs fits the computational mindset of software system engineers and is supported by a…
Natural language programming is a promising approach to enable end users to instruct new tasks for intelligent agents. However, our formative study found that end users would often use unclear, ambiguous or vague concepts when naturally…
Deep learning continues to revolutionize an ever-growing number of critical application areas including healthcare, transportation, finance, and basic sciences. Despite their increased predictive power, model transparency and human…
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…
When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format…