Generative AI Evaluation

Ask about this topic

Overview

The field asks whether generated text, images, audio, video, and other artifacts meet users’ goals—not just whether they resemble a reference. Common approaches include reference and embedding metrics, distribution distances such as FID and MMD, rubric-based LLM judges, pairwise preference comparisons, and expert or user studies. Task-specific benchmarks increasingly test dimensions such as faithfulness, constraint following, multimodal synchronization, robustness, and performance in complete workflows. A central challenge is that automated scores can disagree with people or miss important failures, so evaluations need clearer constructs, uncertainty estimates, human validation, and evidence of real-world utility.

Latest papers

CardsList

313 papers38 papers in the last four weeks, up 3% on the four weeks before. 0.2% of all new papers.

Oct 17, 2025

AtomBench: A Benchmarking Framework for Generative Crystal Reconstruction Models in Conventional Superconductors

A key question in benchmarking generative crystal reconstruction models is how the amount and type of crystallographic information provided to a generative model affects its ability to reconstruct atomic structures. Yet such comparisons often overlook the fact that models receive unequal information about the target during reconstruction, thereby confounding architectural conclusions. We present AtomBench, an extensible, model-agnostic framework for comparing generative models on a well-defined crystal reconstruction task (rather than de novo generation), which we here apply to conventional superconductors. We train and evaluate four models, AtomGPT, CDVAE, FlowMM, and MatterGen, on the JARVIS Supercon-3D and Alexandria DS-A/B datasets, grouping them by the information each accesses at inference. Reconstruction fidelity is measured by the Kullback-Leibler divergence (KLD) and mean absolute error (MAE) of lattice parameters and the root-mean-squared displacement (RMSD) of atomic coordinates. We further introduce the continuous corrected RMSD (ccRMSD), a continuous measure of local geometric fidelity defined for every structure in the test set. MatterGen achieves the best atomic-coordinate reconstruction, followed by AtomGPT, while CDVAE reconstructs lattices most accurately, and FlowMM is the least accurate but fastest overall. We find that conditioning on critical temperature Tc_c does not consistently improve fidelity. We also release AtomBench as an open-source Python package that reproduces all reported reconstruction metrics, figures, and tables from one or more benchmark files and supports direct submission to the JARVIS-Leaderboard. Any inverse model emitting crystal reconstructions can be benchmarked with atombench, and we encourage community use. https://github.com/atomgptlab/atombench

Charles Rhys Campbell, Aldo H. Romero, Kamal Choudhary

Department of Physics and Astronomy, West Virginia University, Morgantown, WV 26506, USA · Department of Materials Science and Engineering, Whiting School of Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA · Department of Electrical and Computer Engineering, Whiting School of Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA

Materials ScienceGenerative ModelingGenerative AI Evaluation
AskPDF
Oct 14, 2025

Generative AI and Sales Productivity: Field Experiments in Online Retail

We quantify the short-term impact of Generative Artificial Intelligence (GenAI) on sales performance through a series of large-scale randomized field experiments involving millions of users and products at a leading cross-border online retail platform. Over 2023-2024, the platform integrated GenAI into seven business workflows spanning customer service, consumer-product matching, advertising, and seller services. We find that GenAI adoption increases sales in most workflows, with effects ranging from no detectable impact to 16.3%16.3\%, depending on GenAI's marginal contribution relative to baseline firm practices. Across the four GenAI applications with positive sales effects, the implied annual incremental value is roughly \5perconsumer per consumer-$an economically meaningful impact given the retailer's scale and the early stage of GenAI adoption. The gains operate primarily through higher conversion rates rather than larger cart values, consistent with GenAI improving the shopping experience by reducing search, information, communication, and personalization frictions. Importantly, these effects are not associated with worse post-purchase outcomes, as product return rates and customer ratings do not deteriorate. Finally, we document substantial demand-side heterogeneity, with larger gains for less experienced consumers. Our findings provide novel, large-scale causal evidence on how GenAI shapes sales productivity in online retail, highlighting both its immediate value and broader potential.

Lu Fang, Zhe Yuan, Kaifu Zhang +2

†School of Management, Zhejiang University of Finance & Economics; Laboratory for Human-AI Collaboration and Digital Intelligence Innovation, Zhejiang University · ‡Corresponding author. Center for Research of Private Economy, School of Economics, Future Regional Development Laboratory, and Academy of Financial Research, Zhejiang University · §Partner Company +2

Generative AI Evaluation
AskPDF
Oct 1, 2025

Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers

AI answer engines are a relatively new kind of information search tool: rather than returning a ranked list of documents, they generate an answer to a search question with inline citations to sources. But reading the cited sources is costly, and citation links themselves offer little guidance about what evidence they contain. We present attribution gradients, a technique to boost the informativeness of citations by consolidating scent and information prey in place. Its first feature is bringing evidence counts, supporting/contradictory excerpts, links to sources, and contextual explanations into one place. Its second feature is the ability to unravel second-degree citations in place. In a lab study, we demonstrate usage of the full gradient in a critical reading task and its support for deep engagement that increased the depth of what readers took away from the sources versus a standard citation and document QA design.

Hita Kambhamettu, Alyssa Hwang, Philippe Laban +1

University of Pennsylvania, Philadelphia, PA, USA · Microsoft Research, New York, NY, USA

Information DesignClaim Attribution in Language ModelsGenerative AI Evaluation
AskPDF
Sep 23, 2025

Measuring AI "Slop" in Text

AI "slop" is an increasingly popular term used to describe low-quality AI-generated text, but there is currently no agreed upon definition of this term nor a means to measure its occurrence. In this work, we develop a taxonomy of "slop" through interviews with experts in NLP, writing, and philosophy, and propose a set of interpretable dimensions for its assessment in text. Through span-level annotation, we find that binary "slop" judgments are (somewhat) subjective, but such determinations nonetheless correlate with latent dimensions such as coherence and relevance. Our framework can be used to examine AI-generated text in both detection and binary preference tasks, potentially offering new insights into the linguistic and stylistic factors that contribute to quality judgments. We highlight that fully automated and scalable methods remain an open challenge.

Chantal Shaib, Tuhin Chakrabarty, Diego Garcia-Olano +1

Northeastern University · Stony Brook University · Meta AI

Generative AI EvaluationLanguage Model Generation Evaluation
AskPDF
Sep 15, 2025

Generative AI performance in core undergraduate mathematics: a curriculum-level case study

Generative artificial intelligence (GenAI) tools such as OpenAI's ChatGPT are transforming the educational landscape, prompting reconsideration of traditional assessment practices. In parallel, universities are exploring alternatives to in-person, closed-book examinations, raising concerns about academic integrity and pedagogical alignment in uninvigilated settings. This study systematically investigates the performance of GenAI on typical mathematics questions from across a first-year mathematics curriculum. Adopting an empirical approach and utilising current examination questions as a proxy for course content, we generate, transcribe, and blind-mark GenAI submissions to eight undergraduate mathematics assessments, spanning the entirety of the first-year curriculum. By combining independent GenAI responses to individual questions, we enable a meaningful evaluation of GenAI performance, both at the level of modules and across the first-year curriculum. We find that GenAI attainment is at the level of a first-class degree, though current performance can vary between modules. Further, we find that GenAI performance is remarkably consistent when viewed across the entire curriculum, significantly more so than that of students in invigilated examinations. Our findings evidence the pressing need for redesigning assessments in mathematics in the era of generative artificial intelligence.

Benjamin J. Walker, Nikoleta Kalaydzhieva, Beatriz Navarro Lameda +1

Department of Mathematics, University College London, Gordon Street, WC1H 0AY, London, UK

Educational AssessmentGenerative AI in EducationLLM Mathematical ReasoningGenerative AI Evaluation
AskPDF
Aug 19, 2025

Towards AI-Assisted Research Writing: Benchmarking LLMs for AI/ML Introduction Generation

As researchers increasingly adopt LLMs as writing assistants, generating high-quality research paper introductions remains both challenging and essential. We introduce Scientific Introduction Generation (SciIG), a task that evaluates LLMs' ability to produce coherent introductions from titles, abstracts, and related works. Curating new datasets from NAACL 2025 and ICLR 2025 papers, we assess five state-of-the-art models, including both open-source (DeepSeek-v3, Gemma-3-12B, LLaMA 4-Maverick, MistralAI Small 3.1) and closed-source GPT-4o systems, across multiple dimensions: lexical overlap, semantic similarity, content coverage, faithfulness, consistency, citation correctness, and narrative quality. Our comprehensive framework combines automated metrics with LLM-as-a-judge evaluations. Results demonstrate LLaMA-4 Maverick's superior performance on most metrics, particularly in semantic similarity and faithfulness. Moreover, three-shot prompting consistently outperforms fewer-shot approaches. These findings provide practical insights into developing effective research writing assistants and set realistic expectations for LLM-assisted academic writing. To foster re- producibility and future research, we publicly release all code and datasets.

Krishna Garg, Firoz Shaik, Sambaran Bandyopadhyay +1

University of Illinois Chicago · Adobe Research

LLM EvaluationLanguage Model Generation EvaluationLLM PromptingAI-Assisted Scientific ResearchGenerative AI Evaluation
AskPDF
Aug 8, 2025

Evaluating Style-Personalized Text Generation: Challenges and Directions

With the surge of large language models (LLMs) and their ability to produce customized output, style-personalized text generation--"write like me"--has become a rapidly growing area of interest. However, style personalization is highly specific, relative to every user, and depends strongly on the pragmatic context, which makes it uniquely challenging. Although prior research has introduced benchmarks and metrics for this area, they tend to be non-standardized and have known limitations (e.g., poor correlation with human subjects). LLMs have been found to not capture author-specific style well, it follows that the metrics themselves must be scrutinized carefully. In this work we critically examine the effectiveness of the most common metrics used in the field, such as BLEU, embeddings, and LLMs-as-judges. We evaluate these metrics using our proposed style discrimination benchmark, which spans eight diverse writing tasks across three evaluation settings: domain discrimination, authorship attribution, and LLM-generated personalized vs non-personalized discrimination. We find strong evidence that employing ensembles of diverse evaluation metrics consistently outperforms single-evaluator methods, and conclude by providing guidance on how to reliably assess style-personalized text generation.

Anubhav Jangra, Bahareh Sarrafzadeh, Silviu Cucerzan +2

Columbia University, USA · Microsoft, USA · The University of York, UK

LLM-as-a-JudgeLanguage Model Generation EvaluationPersonalized Text GenerationAutomated EvaluationGenerative AI Evaluation
AskPDF
Mar 24, 2025

PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models

Deep generative models (DGMs) have caused a paradigm shift in the field of machine learning, yielding noteworthy advancements in domains such as image synthesis, natural language processing, and other related areas. However, a comprehensive evaluation of these models that effectively captures the interplay among fidelity, diversity, and novelty in generated samples remains a persistent challenge. A recently proposed approach, the Feature Likelihood Divergence (FLD), offers a theoretically grounded and practical tool in this regard but faces notable computational limitations. In this paper, we propose PALATE, a novel framework designed to enhance the evaluation of DGMs by addressing the efficiency constraints of FLD. Our approach is based on a peculiar application of the law of total expectation to random variables representing accessible data. When integrated with the MMD baseline metric and the recently introduced DINOv3 feature extractor, PALATE provides a comprehensive evaluation framework that matches or exceeds state-of-the-art methods while offering superior computational efficiency and scalability to large-scale datasets. Through a series of experiments, we demonstrate that the PALATE enhancement constitutes a practical and computationally efficient framework for holistic DGM assessment, particularly in detecting sample memorization and evaluating generalization capabilities. The source code is provided as supplementary material.

Tadeusz Dziarmaga, Marcin Kądziołka, Laura Musioł +4

Jagiellonian University, Faculty of Mathematics and Computer Science, Kraków, Poland · Jagiellonian University, Doctoral School of Exact and Natural Sciences, Kraków, Poland

Generative AI EvaluationGenerative Modeling
AskPDF
Dec 11, 2024

Competition and Diversity in Generative AI

Recent evidence, both in the lab and in the wild, suggests that the use of generative artificial intelligence reduces the diversity of content produced. The use of the same or similar AI models appears to lead to more homogeneous behavior. Our work begins with the observation that there is a force pushing in the opposite direction: competition. When producers compete with one another (e.g., for customers or attention), they are incentivized to create novel or unique content. We explore the impact competition has on both content diversity and overall social welfare. Through a formal game-theoretic model, we show that competitive markets select for diverse AI models, mitigating monoculture. We further show that a generative AI model that performs well in isolation (i.e., according to a benchmark) may fail to provide value in a competitive market. Our results highlight the importance of evaluating generative AI models across the breadth of their output distributions, particularly when they will be deployed in competitive environments. We validate our results empirically by using language models to play Scattergories, a word game in which players are rewarded for answers that are both correct and unique. Overall, our results suggest that homogenization due to generative AI is unlikely to persist in competitive markets, and instead, competition in downstream markets may drive diversification in AI model development.

Manish Raghavan

MIT Sloan School of Management & Department of Electrical Engineering and Computer Science.

Output Diversity in Language ModelsGenerative AI Evaluation
AskPDF
Nov 5, 2024

Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs

Generative models guided by text prompts are widely evaluated for fidelity and prompt alignment, yet their ability to produce diverse outputs remains underexplored. Existing diversity metrics such as Vendi and RKE, which are based on the von Neumann and Rényi entropies of kernel matrices, were developed for unconditional models and cannot distinguish prompt-induced from model-induced variability. We address this gap by introducing Conditional-Vendi and Conditional-RKE, diversity measures derived from the conditional entropy of positive semidefinite matrices. These scores isolate model-induced diversity in prompt-guided generation, with Conditional-RKE enjoying an O(1/n)O(1/\sqrt{n}) convergence rate. For Conditional-Vendi, we introduce a truncated-spectrum approximation that yields scalable and consistent estimates. Experiments on text-to-image, image-captioning, and LLM tasks show that the conditional scores recover ground-truth diversity orderings and can also guide diffusion models toward more diverse samples. The codebase is available at https://github.com/mjalali/conditional-vendi.

Mohammad Jalali, Azim Ospanov, Amin Gohari +1

Department of Computer Science and Engineering, The Chinese University of Hong Kong · Department of Information Engineering, The Chinese University of Hong Kong

Generative AI EvaluationLanguage Model Generation EvaluationT2I Generation Evaluation
AskPDF
May 27, 2024

Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders

The rapid growth of scientific literature makes it increasingly challenging for researchers to identify novel and impactful ideas, especially across disciplines. Modern artificial intelligence (AI) systems offer new opportunities for scientific ideation, but how compelling are AI-generated ideas, and how can their quality be improved? Here, we introduce SciMuse, which generates personalized research ideas using a knowledge graph of 58 million papers and a large language model (LLM). A central focus of this work is to understand how interesting these ideas are. Therefore, we conducted a large-scale evaluation in which more than 100 research group leaders -- spanning the natural sciences to the humanities -- rated over 4,400 personalized ideas according to their level of interest. Overall, expert ratings were modest (mean 2.40 on a 5-point scale, most common rating 1), while 24.9% of ideas were rated 4 or 5. We find that supplying concept pairs selected using the knowledge graph does not improve expert-rated interest over a titles-only GPT baseline. High-citation-predicted pairs even showed a weak tendency (1.94σσ) toward lower interest than random pairs. Nevertheless, graph features can be used to control properties of ideas, and, using this unique evaluation dataset, we show that idea interest can be predicted with both a supervised neural network based on graph features and a zero-shot ranking approach based on an LLM. Our work provides an AI methodology for generating scientific ideas and a large-scale interdisciplinary expert evaluation, paving the way to study and improve difficult-to-measure metrics such as expert-perceived scientific interestingness.

Xuemei Gu, Mario Krenn

Max Planck Institute for the Science of Light, Staudtstrasse 2, 91058 Erlangen, Germany

AI-Assisted Scientific ResearchScientific Hypothesis GenerationResearch Idea GenerationLarge Language Model-Guided Scientific DiscoveryGenerative AI EvaluationScientific Idea Evaluation
AskPDF
Feb 6, 2024

PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation

We propose a likelihood-free method for comparing two distributions given samples from each, with the goal of assessing the quality of generative models. The proposed approach, PQMass, provides a statistically rigorous method for assessing the performance of a single generative model or the comparison of multiple competing models. PQMass divides the sample space into non-overlapping regions and applies chi-squared tests to the number of data samples that fall within each region, giving a p-value that measures the probability that the bin counts derived from two sets of samples are drawn from the same multinomial distribution. PQMass does not depend on assumptions regarding the density of the true distribution, nor does it rely on training or fitting any auxiliary models. We evaluate PQMass on data of various modalities and dimensions, demonstrating its effectiveness in assessing the quality, novelty, and diversity of generated samples. We further show that PQMass scales well to moderately high-dimensional data and thus obviates the need for feature extraction in practical applications.

Pablo Lemos, Sammy Sharief, Esmeralda S. Whitammer +4

1Mila – Québec Artificial Intelligence Institute · 2Ciela Institute · 3Université de Montréal +3

Two-Sample TestingGenerative AI Evaluation
AskPDF
Oct 18, 2023

Consistent Distributed Ranking of Generative Models via Kernel Distances

Ranking generative models based on the fidelity and diversity of their outputs is required to identify the best generator in a group of candidate generative AI models. To rank a group of models in a conventional centralized setting, a standard score is commonly evaluated for each involved model. The selection and design of reference-based evaluation scores have been extensively studied in centralized settings, where the reference samples are drawn from a single probability distribution. However, in practical scenarios including distributed learning contexts, reference samples are distributed across multiple clients, each potentially with a heterogeneous data distribution. In this work, we investigate the ranking of generative models in such distributed settings with heterogeneous data distributions across clients. We focus on the widely used family of kernel distance (KD) evaluation metrics. We prove that, for every kernel function, ranking models by the averaged KD scores of individual clients yields the same ordering as a centralized KD evaluation using the combined reference data from all the clients. We further extend our analysis to other popular metrics, including the Fréchet Distance (FD), for which the individual client scores could be insufficient for accurate model ranking. We present the numerical results of several experiments on standard image datasets and generative models to validate our theoretical findings regarding distributed ranking using various evaluation scores.

Zixiao Wang, Farzan Farnia, Zhenghao Lin +2

Kernel MethodsImage Generation EvaluationGenerative AI Evaluation
AskPDF