activity
20242026
collaborators

10 papers

cs.AI2026

When Do We Need LLMs? A Diagnostic for Language-Driven Bandits

Uljad Berdica, Fernando Acero, Anton Ipsen +3

We study Contextual Multi-Armed Bandits (CMABs) for non-episodic decision-making problems where the context includes both textual and numerical information (e.g., recommendation sy…

cs.LG2026

ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values

Tom Bewley, Salim I. Amoukou, Emanuele Albini +2

Changes in input distribution can induce shifts in the average predictions of machine learning models. Such prediction shifts may impact downstream business outcomes (e.g. a bank's…

cs.AI2026

Beyond Manual Planning: Seating Allocation for Large Organizations

Anton Ipsen, Michael Cashmore, Kirsty Fielding +4

We introduce the Hierarchical Seating Allocation Problem (HSAP) which addresses the optimal assignment of hierarchically structured organizational teams to physical seating arrange…

cs.LG2025

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models

Anna Hedström, Salim I. Amoukou, Tom Bewley +2

We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventi…

cs.DC2025

Capacity Planning and Scheduling for Jobs with Uncertainty in Resource Usage and Duration

Sunandita Patra, Mehtab Pathan, Mahmoud Mahfouz +4

Organizations around the world schedule jobs (programs) regularly to perform various tasks dictated by their end users. With the major movement towards using a cloud computing infr…

cs.LG2025

Interpreting Language Reward Models via Contrastive Explanations

Junqi Jiang, Tom Bewley, Saumitra Mishra +2

Reward models (RMs) are a crucial component in the alignment of large language models' (LLMs) outputs with human values. RMs approximate human preferences over possible LLM respons…