arXiv subjects

Lorenzo Pacchiardi

Publications and source records attributed to Lorenzo Pacchiardi.

At least 19 recordsLinked to original sources

arXiv2026

Europe and the Geopolitics of AGI: The Need for a Preparedness Plan

Artificial general intelligence (AGI)--defined here as AI systems that match or exceed humans at most economically useful cognitive work--has moved from speculation to the centre of political and strategic debate. This paper examines three questions: how soon AGI might emerge, how it could reshape geopolitics, and whether Europe is adequately prepared. Drawing on empirical trends in AI capabilities, expert forecasting surveys, and policy analysis, we find that a plausible window for AGI emergence falls between 2030 and 2040, or potentially earlier, though substantial uncertainty remains. Our analysis of the geopolitical implications suggests that AGI could fundamentally alter the global distribution of economic and military power, intensify interstate competition, and strain existing governance frameworks. Assessing Europe's current positioning, we identify critical gaps: limited strategic awareness of frontier AI progress, structural weaknesses in compute infrastructure and talent retention, low rates of industrial AI adoption, and fragmented policy responses at both EU and Member State levels that do not match the potential scale of disruption.These findings point to a need for a coordinated European preparedness agenda. We outline policy options centred on building institutional capacity for AGI situational awareness, strengthening Europe's position in the AI value chain, and developing frameworks for international stability in an era of increasingly capable AI systems.

cs.CY↗

arXiv2026

Seven simple steps for log analysis in AI systems

AI systems produce large volumes of logs as they interact with tools and users. Analysing these logs can help understand model capabilities, propensities, and behaviours, or assess whether an evaluation worked as intended. Researchers have started developing methods for log analysis, but a standardised approach is still missing. Here we suggest a pipeline based on current best practices. We illustrate it with concrete code examples in the Inspect Scout library, provide detailed guidance on each step, and highlight common pitfalls. Our framework provides researchers with a foundation for rigorous and reproducible log analysis.

cs.AI↗

arXiv2026

No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes

Do large language models (LLMs) anticipate when they will answer correctly? To study this, we extract activations after a question is read but before any tokens are generated, and train linear probes to predict whether the model's forthcoming answer will be correct. Across three open-source model families ranging from 7 to 70 billion parameters, projections on this "in-advance correctness direction" trained on generic trivia questions predict success in distribution and on diverse out-of-distribution knowledge datasets, indicating a deeper signal than dataset-specific spurious features, and outperforming black-box baselines and verbalised predicted confidence. Predictive power saturates in intermediate layers and, notably, generalisation falters on questions requiring mathematical reasoning. Moreover, for models responding "I don't know", doing so strongly correlates with the probe score, indicating that the same direction also captures confidence. By complementing previous results on truthfulness and other behaviours obtained with probes and sparse auto-encoders, our work contributes essential findings to elucidate LLM internals.

cs.CL↗

arXiv2026

Capabilities Ain't All You Need: Measuring Propensities in AI

AI evaluation has primarily focused on measuring capabilities, with formal approaches inspired from Item Response Theory (IRT) being increasingly applied. Yet propensities - the tendencies of models to exhibit particular behaviours - play a central role in determining both performance and safety outcomes. However, traditional IRT describes a model's success on a task as a monotonic function of model capabilities and task demands, an approach unsuited to propensities, where both excess and deficiency can be problematic. Here, we introduce the first formal framework for measuring AI propensities by using a bilogistic formulation for model success, which attributes high success probability when the model's propensity is within an "ideal band". Further, we estimate the limits of the ideal band using LLMs equipped with newly developed task-agnostic rubrics. Applying our framework to six families of LLM models whose propensities are incited in either direction, we find that we can measure how much the propensity is shifted and what effect this has on the tasks. Critically, propensities estimated using one benchmark successfully predict behaviour on held-out tasks. Moreover, we obtain stronger predictive power when combining propensities and capabilities than either separately. More broadly, our framework showcases how rigorous propensity measurements can be conducted and how it yields gains over solely using capability evaluations to predict AI behaviour.

cs.LG↗

arXiv2026

Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies

We outline a vision for frontier AI auditing, which we define as rigorous third-party verification of frontier AI developers' safety and security claims, and evaluation of their systems and practices against relevant standards, based on deep, secure access to non-public information. Frontier AI audits should not be limited to a company's publicly deployed products, but should instead consider the full range of organization-level safety and security risks, including internal deployment of AI systems, information security practices, and safety decision-making processes. We describe four AI Assurance Levels (AALs), the higher levels of which provide greater confidence in audit findings. We recommend AAL-1 as a baseline for frontier AI generally, and AAL-2 as a near-term goal for the most advanced subset of frontier AI developers. Achieving the vision we outline will require (1) ensuring high quality standards for frontier AI auditing, so it does not devolve into a checkbox exercise or lag behind changes in the industry; (2) growing the ecosystem of audit providers at a rapid pace without compromising quality; (3) accelerating adoption of frontier AI auditing by clarifying and strengthening incentives; and (4) achieving technical readiness for high AI Assurance Levels so they can be applied when needed.

cs.CY↗

arXiv2025

Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents

Data science aims to extract insights from data to support decision-making processes. Recently, Large Language Models (LLMs) have been increasingly used as assistants for data science, by suggesting ideas, techniques and small code snippets, or for the interpretation of results and reporting. Proper automation of some data-science activities is now promised by the rise of LLM agents, i.e., AI systems powered by an LLM equipped with additional affordances--such as code execution and knowledge bases--that can perform self-directed actions and interact with digital environments. In this paper, we survey the evaluation of LLM assistants and agents for data science. We find (1) a dominant focus on a small subset of goal-oriented activities, largely ignoring data management and exploratory activities; (2) a concentration on pure assistance or fully autonomous agents, without considering intermediate levels of human-AI collaboration; and (3) an emphasis on human substitution, therefore neglecting the possibility of higher levels of automation thanks to task transformation.

cs.AI↗

arXiv2025

PredictaBoard: Benchmarking LLM Score Predictability

Despite possessing impressive skills, Large Language Models (LLMs) often fail unpredictably, demonstrating inconsistent success in even basic common sense reasoning tasks. This unpredictability poses a significant challenge to ensuring their safe deployment, as identifying and operating within a reliable "safe zone" is essential for mitigating risks. To address this, we present PredictaBoard, a novel collaborative benchmarking framework designed to evaluate the ability of score predictors (referred to as assessors) to anticipate LLM errors on specific task instances (i.e., prompts) from existing datasets. PredictaBoard evaluates pairs of LLMs and assessors by considering the rejection rate at different tolerance errors. As such, PredictaBoard stimulates research into developing better assessors and making LLMs more predictable, not only with a higher average performance. We conduct illustrative experiments using baseline assessors and state-of-the-art LLMs. PredictaBoard highlights the critical need to evaluate predictability alongside performance, paving the way for safer AI systems where errors are not only minimised but also anticipated and effectively mitigated. Code for our benchmark can be found at https://github.com/Kinds-of-Intelligence-CFI/PredictaBoard

cs.CL↗

arXiv2025

Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture

Research in AI evaluation has grown increasingly complex and multidisciplinary, attracting researchers with diverse backgrounds and objectives. As a result, divergent evaluation paradigms have emerged, often developing in isolation, adopting conflicting terminologies, and overlooking each other's contributions. This fragmentation has led to insular research trajectories and communication barriers both among different paradigms and with the general public, contributing to unmet expectations for deployed AI systems. To help bridge this insularity, in this paper we survey recent work in the AI evaluation landscape and identify six main paradigms. We characterise major recent contributions within each paradigm across key dimensions related to their goals, methodologies and research cultures. By clarifying the unique combination of questions and approaches associated with each paradigm, we aim to increase awareness of the breadth of current evaluation approaches and foster cross-pollination between different paradigms. We also identify potential gaps in the field to inspire future research directions.

cs.AI↗

arXiv2025

General Scales Unlock AI Evaluation with Explanatory and Predictive Power

Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activities. So far, benchmarking has guided progress in AI, but it has offered limited explanatory and predictive power for general-purpose AI systems, given the low transferability across diverse tasks. In this paper, we introduce general scales for AI evaluation that can explain what common AI benchmarks really measure, extract ability profiles of AI systems, and predict their performance for new task instances, in- and out-of-distribution. Our fully-automated methodology builds on 18 newly-crafted rubrics that place instance demands on general scales that do not saturate. Illustrated for 15 large language models and 63 tasks, high explanatory power is unleashed from inspecting the demand and ability profiles, bringing insights on the sensitivity and specificity exhibited by different benchmarks, and how knowledge, metacognition and reasoning are affected by model size, chain-of-thought and distillation. Surprisingly, high predictive power at the instance level becomes possible using these demand levels, providing superior estimates over black-box baseline predictors based on embeddings or finetuning, especially in out-of-distribution settings (new tasks and new benchmarks). The scales, rubrics, battery, techniques and results presented here represent a major step for AI evaluation, underpinning the reliable deployment of AI in the years ahead. (Collaborative platform: https://kinds-of-intelligence-cfi.github.io/ADELE.)

cs.AI↗

arXiv2024

Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers

The integrity of AI benchmarks is fundamental to accurately assess the capabilities of AI systems. The internal validity of these benchmarks - i.e., making sure they are free from confounding factors - is crucial for ensuring that they are measuring what they are designed to measure. In this paper, we explore a key issue related to internal validity: the possibility that AI systems can solve benchmarks in unintended ways, bypassing the capability being tested. This phenomenon, widely known in human and animal experiments, is often referred to as the 'Clever Hans' effect, where tasks are solved using spurious cues, often involving much simpler processes than those putatively assessed. Previous research suggests that language models can exhibit this behaviour as well. In several older Natural Language Processing (NLP) benchmarks, individual $n$-grams like "not" have been found to be highly predictive of the correct labels, and supervised NLP models have been shown to exploit these patterns. In this work, we investigate the extent to which simple $n$-grams extracted from benchmark instances can be combined to predict labels in modern multiple-choice benchmarks designed for LLMs, and whether LLMs might be using such $n$-gram patterns to solve these benchmarks. We show how simple classifiers trained on these $n$-grams can achieve high scores on several benchmarks, despite lacking the capabilities being tested. Additionally, we provide evidence that modern LLMs might be using these superficial patterns to solve benchmarks. This suggests that the internal validity of these benchmarks may be compromised and caution should be exercised when interpreting LLM performance results on them.

cs.CL↗

arXiv2024

100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances

Predicting the performance of LLMs on individual task instances is essential to ensure their reliability in high-stakes applications. To do so, a possibility is to evaluate the considered LLM on a set of task instances and train an assessor to predict its performance based on features of the instances. However, this approach requires evaluating each new LLM on a sufficiently large set of task instances to train an assessor specific to it. In this work, we leverage the evaluation results of previously tested LLMs to reduce the number of evaluations required to predict the performance of a new LLM. In practice, we propose to test the new LLM on a small set of reference instances and train a generic assessor which predicts the performance of the LLM on an instance based on the performance of the former on the reference set and features of the instance of interest. We conduct empirical studies on HELM-Lite and KindsOfReasoning, a collection of existing reasoning datasets that we introduce, where we evaluate all instruction-fine-tuned OpenAI models until the January 2024 version of GPT4. When predicting performance on instances with the same distribution as those used to train the generic assessor, we find this achieves performance comparable to the LLM-specific assessors trained on the full set of instances. Additionally, we find that randomly selecting the reference instances performs as well as some advanced selection methods we tested. For out of distribution, however, no clear winner emerges and the overall performance is worse, suggesting that the inherent predictability of LLMs is low.

cs.CL↗

arXiv2024

Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization

Probabilistic forecasting relies on past observations to provide a probability distribution for a future outcome, which is often evaluated against the realization using a scoring rule. Here, we perform probabilistic forecasting with generative neural networks, which parametrize distributions on high-dimensional spaces by transforming draws from a latent variable. Generative networks are typically trained in an adversarial framework. In contrast, we propose to train generative networks to minimize a predictive-sequential (or prequential) scoring rule on a recorded temporal sequence of the phenomenon of interest, which is appealing as it corresponds to the way forecasting systems are routinely evaluated. Adversarial-free minimization is possible for some scoring rules; hence, our framework avoids the cumbersome hyperparameter tuning and uncertainty underestimation due to unstable adversarial training, thus unlocking reliable use of generative networks in probabilistic forecasting. Further, we prove consistency of the minimizer of our objective with dependent data, while adversarial training assumes independence. We perform simulation studies on two chaotic dynamical models and a benchmark data set of global weather observations; for this last example, we define scoring rules for spatial data by drawing from the relevant literature. Our method outperforms state-of-the-art adversarial approaches, especially in probabilistic calibration, while requiring less hyperparameter tuning.

stat.ML↗

arXiv2023

How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions

Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense. LLMs might "lie", for example, when instructed to output misinformation. Here, we develop a simple lie detector that requires neither access to the LLM's activations (black-box) nor ground-truth knowledge of the fact in question. The detector works by asking a predefined set of unrelated follow-up questions after a suspected lie, and feeding the LLM's yes/no answers into a logistic regression classifier. Despite its simplicity, this lie detector is highly accurate and surprisingly general. When trained on examples from a single setting -- prompting GPT-3.5 to lie about factual questions -- the detector generalises out-of-distribution to (1) other LLM architectures, (2) LLMs fine-tuned to lie, (3) sycophantic lies, and (4) lies emerging in real-life scenarios such as sales. These results indicate that LLMs have distinctive lie-related behavioural patterns, consistent across architectures and contexts, which could enable general-purpose lie detection.

cs.CL↗

arXiv2023

Generalized Bayesian Likelihood-Free Inference

We propose a posterior for Bayesian Likelihood-Free Inference (LFI) based on generalized Bayesian inference. To define the posterior, we use Scoring Rules (SRs), which evaluate probabilistic models given an observation. In LFI, we can sample from the model but not evaluate the likelihood; hence, we employ SRs which admit unbiased empirical estimates. We use the Energy and Kernel SRs, for which our posterior enjoys consistency in a well-specified setting and outlier robustness. We perform inference with pseudo-marginal (PM) Markov Chain Monte Carlo (MCMC) or stochastic-gradient (SG) MCMC. While PM-MCMC works satisfactorily for simple setups, it mixes poorly for concentrated targets. Conversely, SG-MCMC requires differentiating the simulator model but improves performance over PM-MCMC when both work and scales to higher-dimensional setups as it is rejection-free. Although both techniques target the SR posterior approximately, the error diminishes as the number of model simulations at each MCMC step increases. In our simulations, we employ automatic differentiation to effortlessly differentiate the simulator model. We compare our posterior with related approaches on standard benchmarks and a chaotic dynamical system from meteorology, for which SG-MCMC allows inferring the parameters of a neural network used to parametrize a part of the update equations of the dynamical system.

stat.ME↗

arXiv2022

Likelihood-Free Inference with Generative Neural Networks via Scoring Rule Minimization

Bayesian Likelihood-Free Inference methods yield posterior approximations for simulator models with intractable likelihood. Recently, many works trained neural networks to approximate either the intractable likelihood or the posterior directly. Most proposals use normalizing flows, namely neural networks parametrizing invertible maps used to transform samples from an underlying base measure; the probability density of the transformed samples is then accessible and the normalizing flow can be trained via maximum likelihood on simulated parameter-observation pairs. A recent work [Ramesh et al., 2022] approximated instead the posterior with generative networks, which drop the invertibility requirement and are thus a more flexible class of distributions scaling to high-dimensional and structured data. However, generative networks only allow sampling from the parametrized distribution; for this reason, Ramesh et al. [2022] follows the common solution of adversarial training, where the generative network plays a min-max game against a "critic" network. This procedure is unstable and can lead to a learned distribution underestimating the uncertainty - in extreme cases collapsing to a single point. Here, we propose to approximate the posterior with generative networks trained by Scoring Rule minimization, an overlooked adversarial-free method enabling smooth training and better uncertainty quantification. In simulation studies, the Scoring Rule approach yields better performances with shorter training time with respect to the adversarial framework.

stat.CO↗

arXiv2022

Score Matched Neural Exponential Families for Likelihood-Free Inference

Bayesian Likelihood-Free Inference (LFI) approaches allow to obtain posterior distributions for stochastic models with intractable likelihood, by relying on model simulations. In Approximate Bayesian Computation (ABC), a popular LFI method, summary statistics are used to reduce data dimensionality. ABC algorithms adaptively tailor simulations to the observation in order to sample from an approximate posterior, whose form depends on the chosen statistics. In this work, we introduce a new way to learn ABC statistics: we first generate parameter-simulation pairs from the model independently on the observation; then, we use Score Matching to train a neural conditional exponential family to approximate the likelihood. The exponential family is the largest class of distributions with fixed-size sufficient statistics; thus, we use them in ABC, which is intuitively appealing and has state-of-the-art performance. In parallel, we insert our likelihood approximation in an MCMC for doubly intractable distributions to draw posterior samples. We can repeat that for any number of observations with no additional model simulations, with performance comparable to related approaches. We validate our methods on toy models with known likelihood and a large-dimensional time-series model.

stat.ME↗

arXiv2021

ABCpy: A High-Performance Computing Perspective to Approximate Bayesian Computation

ABCpy is a highly modular scientific library for Approximate Bayesian Computation (ABC) written in Python. The main contribution of this paper is to document a software engineering effort that enables domain scientists to easily apply ABC to their research without being ABC experts; using ABCpy they can easily run large parallel simulations without much knowledge about parallelization. Further, ABCpy enables ABC experts to easily develop new inference schemes and evaluate them in a standardized environment and to extend the library with new algorithms. These benefits come mainly from the modularity of ABCpy. We give an overview of the design of ABCpy and provide a performance evaluation concentrating on parallelization. This points us towards the inherent imbalance in some of the ABC algorithms. We develop a dynamic scheduling MPI implementation to mitigate this issue and evaluate the various ABC algorithms according to their adaptability towards high-performance computing.

stat.CO↗

arXiv2020

Using mobility data in the design of optimal lockdown strategies for the COVID-19 pandemic

A mathematical model for the COVID-19 pandemic spread, which integrates age-structured Susceptible-Exposed-Infected-Recovered-Deceased dynamics with real mobile phone data accounting for the population mobility, is presented. The dynamical model adjustment is performed via Approximate Bayesian Computation. Optimal lockdown and exit strategies are determined based on nonlinear model predictive control, constrained to public-health and socio-economic factors. Through an extensive computational validation of the methodology, it is shown that it is possible to compute robust exit strategies with realistic reduced mobility values to inform public policy making, and we exemplify the applicability of the methodology using datasets from England and France. Code implementing the described experiments is available at https://github.com/OptimalLockdown.

stat.AP↗