works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.CL2026

Constitutional Midtraining: Content Presence Drives Alignment Gains

Desiree Cho, Cameron Tice, Bernie Hogan +4

The paper investigates inserting constitutionally‑derived content during midtraining of large language models to improve the durability of alignment, showing reduced blackmail tend…

cs.AI2026

From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement

Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka

Pluralistic alignment is typically operationalised as preference aggregation: producing responses that span (Overton), steer toward (Steerable), or proportionally represent (Distri…

cs.AI2026

The Evaluation Differential: When Frontier AI Models Recognise They Are Being Tested

Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka +1

Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently represent them, and behave differently under thos…

cs.AI2026

Deployment-Relevant Alignment Cannot Be Inferred from Model-Level Evaluation Alone

Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka +1

Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under fixed inputs, such as truthfulness, instruction f…

cs.CY2026

NeurIPS Should Require Reproducibility Standards for Frontier AI Safety Claims

Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka +1

Frontier AI safety claims - published assertions that a highly capable general-purpose model is below a threshold of concern, adequately mitigated, or suitable for release - increa…

cs.HC2026

The Collaboration Gap in Human-AI Work

Varad Vishwarupe, Marina Jirotka, Nigel Shadbolt +1

LLMs are increasingly presented as collaborators in programming, design, writing, and analysis. Yet the practical experience of working with them often falls short of this promise.…