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