Related papers: iStar 2.0 Language Guide
Computer-assisted language learning -- CALL -- is an established research field. We review how artificial intelligence can be applied to support language learning and teaching. The need for intelligent agents that assist language learners…
Cognitive science faces ongoing challenges in research integration, formalization, conceptual clarity, and other areas, in part due to its multifaceted and interdisciplinary nature. Recent advances in artificial intelligence, particularly…
We report on a half-semester course focused around implementation of type systems in programming languages. The course assumes basics of classical compiler construction, in particular, the abstract syntax representation, the Visitor…
While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored. We leverage advances in language…
The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. Steering abstractions are designed around four model control surfaces: input (modification of the prompt), structural (modification of the…
Language models today are widely used in education, yet their ability to tailor responses for learners with varied informational needs and knowledge backgrounds remains under-explored. To this end, we introduce ELI-Why, a benchmark of 13.4K…
Much of the research focus on AI alignment seeks to align large language models and other foundation models to the context-less and generic values of helpfulness, harmlessness, and honesty. Frontier model providers also strive to align…
This report presents a set of use scenarios based on existing resources that teachers can use as inspiration to create their own, with the aim of introducing artificial intelligence (AI) at different pre-university levels, and with…
In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs). To construct high-quality instruction datasets, many instruction processing…
The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate…
Clarifying user needs is essential for existing task-oriented dialogue systems. However, in real-world applications, developers can never guarantee that all possible user demands are taken into account in the design phase. Consequently,…
Traditional monocular depth estimation suffers from inherent ambiguity and visual nuisances. We demonstrate that language can enhance monocular depth estimation by providing an additional condition (rather than images alone) aligned with…
We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute.…
Context-dependent semantic parsing has proven to be an important yet challenging task. To leverage the advances in context-independent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent…
The Unified Modelling Language is emerging as a de-facto standard for modelling object-oriented systems. However, the semantics document that a part of the standard definition primarily provides a description of the language's syntax and…
Reliable evaluation benchmarks designed for replicability and comprehensiveness have driven progress in machine learning. Due to the lack of a multilingual benchmark, however, vision-and-language research has mostly focused on English…
Feature modeling has been a very popular approach for variability management in software product lines. Building a feature model requires substantial domain expertise, however, even experts cannot foresee all future possibilities. Changing…
Large language models have made significant progress in the past few years. However, they are either generic {\it or} field specific, splitting the community into different groups. In this paper, we unify these large language models into a…
Among the various types of online language learner collective types, we analyze in this contribution Web 2.0 communities featuring an explicit progression. We use three analysis angles (user roles, pedagogical progression and content) in…
As artificial intelligence (AI) increasingly shapes decision-making across domains, there is a growing need to support AI literacy among learners beyond computer science. However, many current approaches rely on programming-heavy tools or…