Related papers: NormCode: A Semi-Formal Language for Auditable AI …
Workflow automation promises substantial productivity gains in everyday document-related tasks. While prior agentic systems can execute isolated instructions, they struggle with automating multi-step, session-level workflows due to limited…
Formal software specification is known to enable early error detection and explicit invariants, yet it has seen limited industrial adoption due to its high notation overhead and the expertise required to use traditional formal languages.…
Natural language is perhaps the most flexible and intuitive way for humans to communicate tasks to a robot. Prior work in imitation learning typically requires each task be specified with a task id or goal image -- something that is often…
AI-assisted research compresses ideation, implementation, evaluation, and manuscript writing into a single interactive loop. This compression is useful, but it also creates a publication risk: paper claims can become easier to state than to…
Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as…
Large Language Models (LLMs) excel in complex reasoning tasks but struggle with consistent rule application, exception handling, and explainability, particularly in domains like legal analysis that require both natural language…
This system demonstration presents Nemo, a new logic programming engine with a focus on reliability and performance. Nemo is built for data-centric analytic computations, modelled in a fully declarative Datalog dialect. Its scalability for…
Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought still operate within…
Indoor scene synthesis underpins embodied AI, robotic manipulation, and simulation-based policy evaluation, where a useful scene must specify not only what the environment looks like, but also how its objects are structured. Existing…
We present the first formalization and metatheory of language soundness for a user-schedulable language, the widely used array processing language Halide. User-schedulable languages strike a balance between abstraction and control in…
Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses atoms, bonds, branches and rings into a compact sequence in…
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…
As automated decision-making solutions are increasingly applied to all aspects of everyday life, capabilities to generate meaningful explanations for a variety of stakeholders (i.e., decision-makers, recipients of decisions, auditors,…
To retrieve and compare scientific data of simulations and experiments in materials science, data needs to be easily accessible and machine readable to qualify and quantify various materials science phenomena. The recent progress in open…
Automated algorithm design is entering a new phase: Large Language Models can now generate full optimisation (meta)heuristics, explore vast design spaces and adapt through iterative feedback. Yet this rapid progress is largely…
One of the most concrete measures to take towards meaningful AI accountability is to consequentially assess and report the systems' performance and impact. However, the practical nature of the "AI audit" ecosystem is muddled and imprecise,…
The uninterpretability of Deep Neural Networks (DNNs) hinders their use in safety-critical applications. Abstract Interpretation-based DNN certifiers provide promising avenues for building trust in DNNs. Unsoundness in the mathematical…
Qualitative coding relies on a researcher's application of codes to textual data. As coding proceeds across large datasets, interpretations of codes often shift (temporal drift), reducing the credibility of the analysis. Existing…
Natural language processing (NLP) aims at investigating the interactions between agents and humans, processing and analyzing large amounts of natural language data. Large-scale language models play an important role in current natural…
Legal practitioners, particularly those early in their careers, face complex, high-stakes tasks that require adaptive, context-sensitive reasoning. While AI holds promise in supporting legal work, current datasets and models are narrowly…