Publications (10)
Contemplative Artificial Intelligence
Ruben Laukkonen, Fionn Inglis, Shamil Chandaria +5
As artificial intelligence (AI) improves, traditional alignment strategies may falter in the face of unpredictable self-improvement, hidden subgoals, and the sheer complexity of in…
Maximum entropy exploration in contextual bandits with neural networks and energy based models
Adam Elwood, Marco Leonardi, Ashraf Mohamed +1
Contextual bandits can solve a huge range of real-world problems. However, current popular algorithms to solve them either rely on linear models, or unreliable uncertainty estimati…
Execution-First Synthetic Tool-Use Trace Generation for LLM Agents
Hafsa Ouajdi, Francesco Giannuzzo, Alaa Boukhary +3
Agentic software-engineering and industrial systems increasingly operate through executable workflows rather than code genera- tion alone: they search artifacts, invoke tools, insp…
Small Encoders Can Rival Large Decoders in Detecting Groundedness
Istabrak Abbes, Gabriele Prato, Quentin Fournier +4
Augmenting large language models (LLMs) with external context significantly improves their performance in natural language processing (NLP) tasks. However, LLMs struggle to answer…
Positive Alignment: Artificial Intelligence for Human Flourishing
Ruben Laukkonen, Seb Krier, Chloé Bakalar +13
Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psych…
Ranking Micro-Influencers: a Novel Multi-Task Learning and Interpretable Framework
Adam Elwood, Alberto Gasparin, Alessandro Rozza
With the rise in use of social media to promote branded products, the demand for effective influencer marketing has increased. Brands are looking for improved ways to identify valu…
An LLM-Based Approach for Insight Generation in Data Analysis
Alberto Sánchez Pérez, Alaa Boukhary, Paolo Papotti +2
Generating insightful and actionable information from databases is critical in data analysis. This paper introduces a novel approach using Large Language Models (LLMs) to automatic…
A survey and taxonomy of loss functions in machine learning
Lorenzo Ciampiconi, Adam Elwood, Marco Leonardi +2
Most state-of-the-art machine learning techniques revolve around the optimisation of loss functions. Defining appropriate loss functions is therefore critical to successfully solvi…
Direct optimisation of the discovery significance when training neural networks to search for new physics in particle colliders
Adam Elwood, Dirk Krücker
We introduce two new loss functions designed to directly optimise the statistical significance of the expected number of signal events when training neural networks to classify eve…
TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction
Qianggang Ding, Haochen Shi, Luis Castejón Lozano +7
We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph…