相关论文: Savile Row Manual

We introduce SafeRL-Lite, an open-source Python library for building reinforcement learning (RL) agents that are both constrained and explainable. Existing RL toolkits often lack native mechanisms for enforcing hard safety constraints or…

Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence. It is an important step towards understanding the meaning of a natural…

Due to their flexibility and superior performance, machine learning models frequently complement and outperform traditional statistical survival models. However, their widespread adoption is hindered by a lack of user-friendly tools to…

Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying "important" pixels in an input image. However, the development and adoption of these methods…

Reducing cost and time required to build high quality software is a major goal for software developers. Building tools and techniques that can help achieve such a goal is the chief aim for Automated Software Engineering (ASE) researchers.…

Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…

Answer Set Programming (ASP) is a declarative logic programming formalism, which is employed nowadays in both academic and industrial real-world applications. Although some tools for supporting the development of ASP programs have been…

Testing autonomous vehicles (AVs) requires complex oracles to determine if the AVs behavior conforms with specifications and humans' expectations. Available open source oracles are tightly embedded in the AV simulation software and are…

Spoken language understanding (SLU) is a task aiming to extract high-level semantics from spoken utterances. Previous works have investigated the use of speech self-supervised models and textual pre-trained models, which have shown…

Many of the core disciplines of artificial intelligence have sets of standard benchmark problems well known and widely used by the community when developing new algorithms. Constraint programming and automated planning are examples of these…

Transformers have gained popularity in the software engineering (SE) literature. These deep learning models are usually pre-trained through a self-supervised objective, meant to provide the model with basic knowledge about a language of…

This technical report describes the usage, syntax, semantics and core algorithms of the probabilistic inductive logic programming framework PrASP. PrASP is a research software which integrates non-monotonic reasoning based on Answer Set…

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…

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged…

This work aims to provide an overview on the open-source multilanguage tool called StyloMetrix. It offers stylometric text representations that cover various aspects of grammar, syntax and lexicon. StyloMetrix covers four languages: Polish…

Simulation is an invaluable tool for developing and evaluating controllers for self-driving cars. Current simulation frameworks are driven by highly-specialist domain specific languages, and so a natural language interface would greatly…

Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque, posing a significant challenge to their safe and reliable deployment. Sparse autoencoders (SAEs) have emerged as a…

Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often…

Although large-scale self-supervised learning (SSL) models like WavLM have achieved state-of-the-art performance in speech processing, their significant size impedes deployment on resource-constrained devices. While structured pruning is a…

Constraint Programming (CP) is a useful technology for modeling and solving combinatorial constrained problems. On the one hand, on can use a library like PyCSP3 for easily modeling problems arising in various application fields (e.g.,…