Riccardo Fogliato

Riccardo Fogliato, Shreya Chappidi, Matthew Lungren et al.

Details of the designs and mechanisms in support of human-AI collaboration must be considered in the real-world fielding of AI technologies. A critical aspect of interaction design for AI-assisted human decision making are policies about the display and sequencing of AI inferences within larger decision-making workflows. We have a poor understanding of the influences of making AI inferences available before versus after human review of a diagnostic task at hand. We explore the effects of providing AI assistance at the start of a diagnostic session in radiology versus after the radiologist has made a provisional decision. We conducted a user study where 19 veterinary radiologists identified radiographic findings present in patients' X-ray images, with the aid of an AI tool. We employed two workflow configurations to analyze (i) anchoring effects, (ii) human-AI team diagnostic performance and agreement, (iii) time spent and confidence in decision making, and (iv) perceived usefulness of the AI. We found that participants who are asked to register provisional responses in advance of reviewing AI inferences are less likely to agree with the AI regardless of whether the advice is accurate and, in instances of disagreement with the AI, are less likely to seek the second opinion of a colleague. These participants also reported the AI advice to be less useful. Surprisingly, requiring provisional decisions on cases in advance of the display of AI inferences did not lengthen the time participants spent on the task. The study provides generalizable and actionable insights for the deployment of clinical AI tools in human-in-the-loop systems and introduces a methodology for studying alternative designs for human-AI collaboration. We make our experimental platform available as open source to facilitate future research on the influence of alternate designs on human-AI workflows.

Riccardo Fogliato, Pratik Patil, Pietro Perona

Matching algorithms are commonly used to predict matches between items in a collection. For example, in 1:1 face verification, a matching algorithm predicts whether two face images depict the same person. Accurately assessing the uncertainty of the error rates of such algorithms can be challenging when data are dependent and error rates are low, two aspects that have been often overlooked in the literature. In this work, we review methods for constructing confidence intervals for error rates in 1:1 matching tasks. We derive and examine the statistical properties of these methods, demonstrating how coverage and interval width vary with sample size, error rates, and degree of data dependence on both analysis and experiments with synthetic and real-world datasets. Based on our findings, we provide recommendations for best practices for constructing confidence intervals for error rates in 1:1 matching tasks.

Valeriia Cherepanova, Chia-Jung Lee, Nil-Jana Akpinar et al.

Large language models (LLMs) have been shown to be effective on tabular prediction tasks in the low-data regime, leveraging their internal knowledge and ability to learn from instructions and examples. However, LLMs can fail to generate predictions that satisfy group fairness, that is, produce equitable outcomes across groups. Critically, conventional debiasing approaches for natural language tasks do not directly translate to mitigating group unfairness in tabular settings. In this work, we systematically investigate four empirical approaches to improve group fairness of LLM predictions on tabular datasets, including fair prompt optimization, soft prompt tuning, strategic selection of few-shot examples, and self-refining predictions via chain-of-thought reasoning. Through experiments on four tabular datasets using both open-source and proprietary LLMs, we show the effectiveness of these methods in enhancing demographic parity while maintaining high overall performance. Our analysis provides actionable insights for practitioners in selecting the most suitable approach based on their specific requirements and constraints.

Gianluca Detommaso, Martin Bertran, Riccardo Fogliato et al.

This paper proposes the use of "multicalibration" to yield interpretable and reliable confidence scores for outputs generated by large language models (LLMs). Multicalibration asks for calibration not just marginally, but simultaneously across various intersecting groupings of the data. We show how to form groupings for prompt/completion pairs that are correlated with the probability of correctness via two techniques: clustering within an embedding space, and "self-annotation" - querying the LLM by asking it various yes-or-no questions about the prompt. We also develop novel variants of multicalibration algorithms that offer performance improvements by reducing their tendency to overfit. Through systematic benchmarking across various question answering datasets and LLMs, we show how our techniques can yield confidence scores that provide substantial improvements in fine-grained measures of both calibration and accuracy compared to existing methods.

Evangelia Spiliopoulou, Riccardo Fogliato, Hanna Burnsky et al.

Large language models (LLMs) can serve as judges that offer rapid and reliable assessments of other LLM outputs. However, models may systematically assign overly favorable ratings to their own outputs, a phenomenon known as self-bias, which can distort evaluations of true model performance. Previous studies often conflate genuine differences in model quality with bias or incorrectly assume that evaluations from LLMs and humans follow the same rating distributions. In this work, we present a statistical framework that explicitly formalizes assumptions under which self-bias can be identified and estimated. Our method models the difference in the scoring distribution that LLM-as-a-judge assigns to its own completions compared to other models, while accounting for the underlying quality of the completions provided by an independent, third-party judge (e.g., humans). Our method reliably isolates and quantifies self-bias, even when models vary in ability, ensuring that genuine performance differences are not mistaken for self-bias. We conduct an empirical analysis of self-bias on a large dataset (>5000 prompt-completion pairs) consisting of expert human annotations and judgments from nine different LLM judges. We find that some models, such as GPT-4o and Claude 3.5 Sonnet, systematically assign higher scores to their own outputs. These models also display family-bias; systematically assigning higher ratings to outputs produced by other models of the same family. Our findings highlight potential pitfalls of using LLM judges and offer practical guidance to mitigate biases when interpreting automated evaluations.

Xiaoyuan Zhu, Kimberly Le Truong, Riccardo Fogliato et al.

As LLMs are deployed in high-stakes settings, users must judge the correctness of individual responses, often relying on model-generated justifications such as reasoning chains or explanations. Yet, no standard measure exists for whether these justifications help users distinguish correct answers from incorrect ones. We formalize this idea as error verifiability and propose $v_{\text{bal}}$, a balanced metric that measures whether justifications enable raters to accurately assess answer correctness, validated against human raters who show high agreement. We find that neither common approaches, such as post-training and model scaling, nor more targeted interventions recommended improve verifiability. We introduce two methods that succeed at improving verifiability: reflect-and-rephrase (RR) for mathematical reasoning and oracle-rephrase (OR) for factual QA, both of which improve verifiability by incorporating domain-appropriate external information. Together, our results establish error verifiability as a distinct dimension of response quality that does not emerge from accuracy improvements alone and requires dedicated, domain-aware methods to address.

Kimberly Le Truong, Riccardo Fogliato, Hoda Heidari et al.

Current benchmarks for evaluating Large Language Models (LLMs) often do not exhibit enough writing style diversity, with many adhering primarily to standardized conventions. Such benchmarks do not fully capture the rich variety of communication patterns exhibited by humans. Thus, it is possible that LLMs, which are optimized on these benchmarks, may demonstrate brittle performance when faced with "non-standard" input. In this work, we test this hypothesis by rewriting evaluation prompts using persona-based LLM prompting, a low-cost method to emulate diverse writing styles. Our results show that, even with identical semantic content, variations in writing style and prompt formatting significantly impact the estimated performance of the LLM under evaluation. Notably, we identify distinct writing styles that consistently trigger either low or high performance across a range of models and tasks, irrespective of model family, size, and recency. Our work offers a scalable approach to augment existing benchmarks, improving the external validity of the assessments they provide for measuring LLM performance across linguistic variations.

Georgy Noarov, Riccardo Fogliato, Martin Bertran et al.

We study the design of adaptive, sequential experiments for unbiased average treatment effect (ATE) estimation in the design-based potential outcomes setting. Our goal is to develop adaptive designs offering sublinear Neyman regret, meaning their efficiency must approach that of the hindsight-optimal nonadaptive design. Recent work [Dai et al, 2023] introduced ClipOGD, the first method achieving $\widetilde{O}(\sqrt{T})$ expected Neyman regret under mild conditions. In this work, we propose adaptive designs with substantially stronger Neyman regret guarantees. In particular, we modify ClipOGD to obtain anytime $\widetilde{O}(\log T)$ Neyman regret under natural boundedness assumptions. Further, in the setting where experimental units have pre-treatment covariates, we introduce and study a class of contextual "multigroup" Neyman regret guarantees: Given any set of possibly overlapping groups based on the covariates, the adaptive design outperforms each group's best non-adaptive designs. In particular, we develop a contextual adaptive design with $\widetilde{O}(\sqrt{T})$ anytime multigroup Neyman regret. We empirically validate the proposed designs through an array of experiments.

Martin Bertran, Riccardo Fogliato, Zhiwei Steven Wu

The conclusions of empirical research depend not only on data but on a sequence of analytic decisions that published results seldom make explicit. Past ``many-analyst" studies have demonstrated this: independent teams testing the same hypothesis on the same dataset regularly reach conflicting conclusions. But such studies require months of coordination among dozens of research groups and are therefore rarely conducted. In this work, we show that fully autonomous AI analysts built on large language models (LLMs) can reproduce a similar structured analytic diversity cheaply and at scale. We task these AI analysts with testing a pre-specified hypothesis on a fixed dataset, varying the underlying model and prompt framing across replicate runs. Each AI analyst independently constructs and executes a full analysis pipeline; an AI auditor then screens each run for methodological validity. Across three datasets spanning experimental and observational designs, AI analyst-produced analyses display wide dispersion in effect sizes, $p$-values, and binary decisions on supporting the hypothesis or not, frequently reversing whether a hypothesis is judged supported. This dispersion is structured: recognizable analytic choices in preprocessing, model specification, and inference differ systematically across LLM and persona conditions. Critically, the effects are \emph{steerable}: reassigning the analyst persona or LLM shifts the distribution of outcomes even after excluding methodologically deficient runs.

Riccardo Fogliato, Pratik Patil, Mathew Monfort et al.

Model performance evaluation is a critical and expensive task in machine learning and computer vision. Without clear guidelines, practitioners often estimate model accuracy using a one-time completely random selection of the data. However, by employing tailored sampling and estimation strategies, one can obtain more precise estimates and reduce annotation costs. In this paper, we propose a statistical framework for model evaluation that includes stratification, sampling, and estimation components. We examine the statistical properties of each component and evaluate their efficiency (precision). One key result of our work is that stratification via k-means clustering based on accurate predictions of model performance yields efficient estimators. Our experiments on computer vision datasets show that this method consistently provides more precise accuracy estimates than the traditional simple random sampling, even with substantial efficiency gains of 10x. We also find that model-assisted estimators, which leverage predictions of model accuracy on the unlabeled portion of the dataset, are generally more efficient than the traditional estimates based solely on the labeled data.

Riccardo Fogliato, Alexandra Chouldechova, Zachary Lipton

As algorithmic risk assessment instruments (RAIs) are increasingly adopted to assist decision makers, their predictive performance and potential to promote inequity have come under scrutiny. However, while most studies examine these tools in isolation, researchers have come to recognize that assessing their impact requires understanding the behavior of their human interactants. In this paper, building off of several recent crowdsourcing works focused on criminal justice, we conduct a vignette study in which laypersons are tasked with predicting future re-arrests. Our key findings are as follows: (1) Participants often predict that an offender will be rearrested even when they deem the likelihood of re-arrest to be well below 50%; (2) Participants do not anchor on the RAI's predictions; (3) The time spent on the survey varies widely across participants and most cases are assessed in less than 10 seconds; (4) Judicial decisions, unlike participants' predictions, depend in part on factors that are orthogonal to the likelihood of re-arrest. These results highlight the influence of several crucial but often overlooked design decisions and concerns around generalizability when constructing crowdsourcing studies to analyze the impacts of RAIs.

Umang Bhatt, Javier Antorán, Yunfeng Zhang et al.

Algorithmic transparency entails exposing system properties to various stakeholders for purposes that include understanding, improving, and contesting predictions. Until now, most research into algorithmic transparency has predominantly focused on explainability. Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders. However, understanding a model's specific behavior alone might not be enough for stakeholders to gauge whether the model is wrong or lacks sufficient knowledge to solve the task at hand. In this paper, we argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. First, we discuss methods for assessing uncertainty. Then, we characterize how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. Finally, we outline methods for displaying uncertainty to stakeholders and recommend how to collect information required for incorporating uncertainty into existing ML pipelines. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness. We aim to encourage researchers and practitioners to measure, communicate, and use uncertainty as a form of transparency.