Related papers: A Benchmark for Scalable Oversight Protocols
Despite the utility of Large Language Models (LLMs) across a wide range of tasks and scenarios, developing a method for reliably evaluating LLMs across varied contexts continues to be challenging. Modern evaluation approaches often use LLMs…
Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…
Benchmarks are pivotal in driving AI progress, and invalid benchmark questions frequently undermine their reliability. Manually identifying and correcting errors among thousands of benchmark questions is not only infeasible but also a…
Major AI ethics guidelines and laws, including the EU AI Act, call for effective human oversight, but do not define it as a distinct and developable capacity. This paper introduces human oversight as a well-being capacity, situated within…
Vibe coding produces correct, executable code at speed, but leaves no record of the structural commitments, dependencies, or evidence behind it. Reviewers cannot determine what invariants were assumed, what changed, or why a regression…
The field of AI research is advancing at an unprecedented pace, enabling automated hypothesis generation and experimental design across diverse domains such as biology, mathematics, and artificial intelligence. Despite these advancements,…
The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a…
Online and AI-based symptom checkers are applications that assist medical laypeople in diagnosing their symptoms and determining which course of action to take. When evaluating these tools, previous studies primarily used an approach…
In the rapidly evolving field of artificial intelligence (AI), traditional benchmarks can fall short in attempting to capture the nuanced capabilities of AI models. We focus on the case of physical world modeling and propose a novel…
Agent-based modelling is a powerful tool when simulating human systems, yet when human behaviour cannot be described by simple rules or maximising one's own profit, we quickly reach the limits of this methodology. Machine learning has the…
Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended…
Artificial intelligence-based systems for player risk detection have become central to harm prevention efforts in the gambling industry. However, growing concerns around transparency and effectiveness have highlighted the absence of…
AI tools to support real world decision making must be able to build simulation models that inform their recommendations and render them interpretable. Tools that can automate aspects of modeling practice must complement human expertise,…
The popularisation of applying AI in businesses poses significant challenges relating to ethical principles, governance, and legal compliance. Although businesses have embedded AI into their day-to-day processes, they lack a unified…
The rapid growth of AI agent ecosystems is transforming how complex tasks are delegated and executed, creating a new challenge of identifying suitable agents for a given task. Unlike traditional tools, agent capabilities are often…
Despite the importance of aligning language models with human preferences, crowd-sourced human feedback is often noisy -- for example, preferring less desirable responses -- posing a fundamental challenge to alignment. A truly robust…
As humans delegate more tasks and decisions to artificial intelligence (AI), we risk losing control of our individual and collective futures. Relatively simple algorithmic systems already steer human decision-making, such as social media…
Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…
Aligning large language models (LLMs) with human values and intents critically involves the use of human or AI feedback. While dense feedback annotations are expensive to acquire and integrate, sparse feedback presents a structural design…
Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…