Related papers: Interpreting and Controlling Model Behavior via Co…

The internal representations learned by deep networks are often sensitive to architecture-specific choices, raising questions about the stability, alignment, and transferability of learned structure across models. In this paper, we…

There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collectively shape the behavior of LM systems that affect them. To…

Mistake detection in procedural tasks is essential for building intelligent systems that support learning and task execution. Existing approaches primarily analyze how an action is performed, while overlooking what it produces, i.e., the…

This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the…

Machine-learned models are often described as "black boxes". In many real-world applications however, models may have to sacrifice predictive power in favour of human-interpretability. When this is the case, feature engineering becomes a…

Large-scale pre-trained language models such as GPT-3 have shown remarkable performance across various natural language processing tasks. However, applying prompt-based methods with GPT-3 for Grammatical Error Correction (GEC) tasks and…

Model transformation tools assist system designers by reducing the labor--intensive task of creating and updating models of various aspects of systems, ensuring that modeling assumptions remain consistent across every model of a system, and…

Action models are semantic structures similar to Kripke models that represent a change in knowledge in an epistemic setting. Whereas the language of action model logic embeds the semantic structure of an action model directly within the…

Artificial neural networks have proven to be extremely useful models that have allowed for multiple recent breakthroughs in the field of Artificial Intelligence and many others. However, they are typically regarded as black boxes, given how…

We present an algebraic semantics for governed execution in which governance is axiomatized, compositional, and coterminous with expressibility. The framework, mechanized in 32 Rocq modules (~12,000 lines, 454 theorems, 0 admitted), is…

The social and implicit nature of human communication ramifies readers' understandings of written sentences. Single gold-standard interpretations rarely exist, challenging conventional assumptions in natural language processing. This work…

Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability in learning symbolic…

Discrete structure rules for validating molecular structures are usually limited to fulfillment of the octet rule or similar simple deterministic heuristics. We propose a model, inspired by language modeling from natural language…

Aerial vehicles are revolutionizing the way film-makers can capture shots of actors by composing novel aerial and dynamic viewpoints. However, despite great advancements in autonomous flight technology, generating expressive camera…

A fundamental question in natural language processing is - what kind of language structure and semantics is the language model capturing? Graph formats such as knowledge graphs are easy to evaluate as they explicitly express language…

Systematic generalization refers to the capacity to understand and generate novel combinations from known components. Despite recent progress by large language models (LLMs) across various domains, these models often fail to extend their…

Multi-modal foundation models combining vision and language models such as Flamingo or GPT-4 have recently gained enormous interest. Alignment of foundation models is used to prevent models from providing toxic or harmful output. While…

Interpreting the meaning of legal open-textured terms is a key task of legal professionals. An important source for this interpretation is how the term was applied in previous court cases. In this paper, we evaluate the performance of GPT-4…

Designing visually diverse and high-quality designs remains a manual, time-consuming process, limiting scalability and personalization in creative workflows. We present a system for generating editable design variations using a decoder-only…

Recent advances in mechanistic interpretability have revealed that large language models (LLMs) develop internal representations corresponding not only to concrete entities but also distinct, human-understandable abstract concepts and…