A computational theory reduces agent evaluation errors and speeds up processes.
problem Efficient evaluation of mini agents at reduced cost.
method Developed a computational theory and a meta-learner to handle heterogeneous agents.
result Reduced evaluation errors by 24.1% to 99.0% across various scenarios.
Study finds AUC is most consistent across different prevalence in binary classification.
problem Consistency of model evaluation metrics across varying prevalence in binary classification.
method Analysis of 156 data scenarios with 18 metrics, 5 models, and a random guess model.
result AUC has the smallest variance in evaluating individual models and ranking of models.
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
Combines curvature descriptors with TDA for graph model evaluation.
problem Evaluating graph generative models efficiently and accurately.
method Combines graph curvature descriptors with topological data analysis.
result Robust, expressive descriptors for graph generative models.
Study evaluates new models using human feedback from another model.
problem Evaluate a new model using human feedback collected for another model.
method Formalize problem, propose model-based and model-free estimators, analyze unbiasedness, and empirically evaluate.
result Proposed estimators can predict absolute values, rank, and optimize evaluated policies.
The paper introduces new metrics for evaluating generative models of behavior.
problem Lack of quantitative evaluation criteria for unsupervised behavior discovery.
method Proposed and investigated several metrics for generative models of behavior.
result The proposed metrics correspond with biologists' intuitions and allow for model evaluation and bias understanding.
We present FIESTA, a model selection approach that significantly reduces the computational resources required to reliably identify state-of-the-art performance from large collections of candidate models. Despite being known to produce unreliable comparisons, it is still common practice to compare model evaluations base…
Geospatial ML models need special evaluation methods due to their unique challenges.
problem Evaluating geospatial machine learning models is challenging due to their specific characteristics.
method Delineated unique challenges and proposed concrete takeaways for improving geospatial model evaluations.
result Concrete takeaways for improving evaluations of geospatial model performance.
New method for evaluating LLMs reduces bias in open-ended evaluations.
problem Bias in Elo-based ratings of LLMs due to data redundancies.
method Proposes evaluation as a 3-player game and introduces novel solution concepts.
result Novel method leads to more robust and intuitive ratings.
SureMap estimates model performance across subpopulations efficiently.
problem Estimating model performance across subpopulations with scarce data.
method Simultaneous Gaussian mean estimation with external data.
result High accuracy in both multi-task and single-task disaggregated evaluations.
Cer-Eval saves LLM evaluation costs while maintaining accuracy.
problem Challenges in evaluating large language models due to large dataset requirements.
method Adapts to different evaluation objectives, uses test sample complexity, and develops a partition-based algorithm.
result Cer-Eval can save 20-40% test points with comparable accuracy and 95% confidence guarantee.
Language model benchmarks often misrepresent true understanding, revealing vulnerabilities in evaluation methods.
problem Language model benchmarks fail to accurately reflect true language understanding and adaptability.
method Systematic analysis of NLP evaluation frameworks, identifying vulnerabilities in static benchmarks, human evaluation protocols, and LLM-as-judge frameworks.
result Current evaluation methods are unreliable and need improvement to accurately assess LLM performance.
FEET protocol evaluates foundation models across three scenarios.
problem Lack of standardized evaluation protocols for foundation models.
method Structured evaluation protocol across three use cases: frozen, few-shot, and fine-tuned embeddings.
result Demonstrates comprehensive assessment of foundation models' effectiveness.
ASEs use surrogate estimation to efficiently evaluate model performance with minimal labels.
problem Efficient model evaluation with limited labels.
method Surrogate-based estimation and active learning.
result ASEs offer greater label-efficiency than current methods for deep neural networks.
The paper proposes a method to evaluate superhuman models by checking for logical inconsistencies.
problem Evaluating superhuman models when ground truth is hard to obtain.
method A framework using consistency checks to identify logical inconsistencies in model decisions.
result Logical inconsistencies can be discovered in superhuman model decisions across various tasks.
Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that model owners and evaluators are hard-pressed analyzing and studying them. This is exacerbated by the complicated procedures for evaluation. The lack of standard systems and efficient techniques for specifying and pro…
Grading function evaluates Bach-style chorales, outperforming human experts.
problem Difficulty in automatically evaluating musical style correctness.
method Introduces a grading function for evaluating four-part chorales in the style of J.S. Bach.
result Transformer model output is outperformed by the grading function at discriminating Bach chorales.
The paper evaluates forecast accuracy of realized volatility measures in large cross-sections.
problem Forecast evaluation of realized volatility measures in large cross-sections of financial data.
method Equal predictive accuracy testing procedures, LASSO shrinkage, measurement error correction, cross-sectional jump component measures.
result The augmented HAR model outperforms the standard HAR model in forecasting realized volatility.
This paper investigates task-level evaluation in few-shot learning models.
problem The reliability of evaluating and tuning models trained for individual tasks in few-shot learning is not well addressed.
method The paper measures accuracy of performance estimators, considers model selection strategies, and examines the reasons for evaluator failure.
result Cross-validation with a low number of folds is best for estimating model performance, while large number of folds is better for model selection.
Study flaws in generative model evaluation metrics, especially for diffusion models.
problem Flaws in existing metrics for evaluating generative models, particularly for diffusion models.
method Systematic study of generative models, human perception experiments, and analysis of feature extractors.
result State-of-the-art perceptual realism of diffusion models is not reflected in commonly reported metrics.
New model improves diversity in question generation over text.
problem Inadequate evaluation metrics for diverse questions.
method Proposed a variational encoder-decoder model and evaluation scheme.
result Improved diversity in generated questions without loss of quality.
Tiny benchmarks reduce LLM evaluation costs by using fewer examples.
problem Expensive evaluation of LLMs with tens of thousands of examples.
method Developed evaluation tools and tiny versions of popular benchmarks.
result Accurately estimate LLM performance with just 100 curated examples.
The DoD needs a robust process to evaluate AI/ML model performance and robustness.
problem AI/ML models are brittle and nonrobust, posing risks in national security.
method Reviews AI/ML development process and best practices for evaluation.
result Recommendations for DoD evaluators to ensure robust AI/ML capabilities.
Study improves machine learning models for GI tract disease detection using comprehensive evaluations and cross-dataset testing.
problem Incomplete or incorrect evaluation of machine learning models for GI tract diseases.
method Comprehensive evaluations of five machine learning models using Global Features and Deep Neural Networks, introducing performance hexagons and cross-dataset testing.
result Demonstrates the need for more sophisticated performance metrics and evaluation methods to build generalizable models.
New framework for interpreting disaggregated fairness evaluations using causal models.
problem Misinterpretation of disaggregated fairness evaluations due to data representativeness and selection bias.
method Causal graphical models to characterize fairness properties and metric stability under different data generating processes.
result Disaggregated evaluations are unreliable without explicit assumptions regarding bias mechanisms.
The paper evaluates variational auto-encoders using model criticism methods.
problem Evaluating the quality of variational auto-encoders (VAEs).
method Statistical model criticism, focusing on reproducing statistics of unknown data generating processes.
result The proposed framework offers possibilities for model selection beyond intrinsic metrics.
Protocol for constructing tailored evaluation datasets for semantic models.
problem Evaluation of domain-specific semantic models, focusing on top ranks.
method Adaptive pairwise comparisons, relatedness-based evaluation dataset, metrics, stochastic transitivity model.
result Effectiveness of the proposed dataset construction protocol confirmed.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
problem Lack of quantitative evaluation criteria for feature-based model explanations.
method Developed quantitative evaluation criteria (low sensitivity, high faithfulness, low complexity), devised a framework for aggregation, and derived a new aggregate Shapley value explanation function.
result A new aggregate Shapley value explanation function that minimizes sensitivity.
New algorithms for model selection in off-policy evaluation of reinforcement learning.
problem Hyperparameter tuning for off-policy evaluation methods in reinforcement learning.
method Developed new model-free and model-based selectors with theoretical guarantees and a new experimental protocol.
result New model-free selector, LSTD-Tournament, demonstrates promising empirical performance.
Study evaluates five LLMs for financial report analysis, revealing performance differences and variability.
problem Lack of understanding in reliability, consistency, and transparency of LLMs in financial analysis.
method Human evaluation, automated similarity metrics, and behavioral diagnostics applied to five transformer-based LLMs over U.S. 10-K filings.
result No single LLM consistently dominates across all evaluation perspectives, highlighting variability and need for interpretability.
Bayesian approach quantifies uncertainty in LLM evaluations.
problem Statistical uncertainty in evaluating LLM behavior.
method Bayesian evaluation of LLM behavior using probabilistic text generation strategies.
result Bayesian approach provides useful uncertainty quantification about LLM behavior.
Topic models are typically evaluated with respect to the global topic distributions that they generate, using metrics such as coherence, but without regard to local (token-level) topic assignments. Token-level assignments are important for downstream tasks such as classification. Even recent models, which aim to improv…
Real world observational data, together with causal inference, allow the estimation of causal effects when randomized controlled trials are not available. To be accepted into practice, such predictive models must be validated for the dataset at hand, and thus require a comprehensive evaluation toolkit, as introduced he…
New models can't beat existing ones, so debiasing methods only slightly reduce needed labels.
problem Limiting scalability in model evaluation due to self-preferencing biases.
method Study of debiasing methods using a few high-quality labels to reduce model judgments.
result Debiasing methods can't decrease required ground truth labels by more than half when the judge is no more accurate than the model.
We present and implement two algorithms for analytic asymptotic evaluation of the marginal likelihood of data given a Bayesian network with hidden nodes. As shown by previous work, this evaluation is particularly hard for latent Bayesian network models, namely networks that include hidden variables, where asymptotic ap…
This paper evaluates metrics for graph generative models, addressing common pitfalls.
problem Evaluating and comparing graph generative models effectively.
method Systematic evaluation of MMD, analysis of synthetic and real graphs, practical recommendations.
result MMD can be problematic; practical solutions are provided.
Our paper improves uplift model evaluation on randomized controlled trials (RCT) data.
problem Variance in uplift evaluation metrics makes their signals arbitrary and unreliable.
method Theoretical analysis and statistical adjustment of the outcome to reduce variance.
result Variance reduction methods improve uplift evaluation metrics on RCT data.
This post introduces model calibration and evaluation measures, highlighting issues with a common measure.
problem Ensuring model confidence accurately reflects true outcomes.
method Explains common calibration definition, ECE, and its drawbacks.
result New evaluation measures needed for comprehensive model calibration.
Paper applies NEAT for dynamic credit evaluation using streaming data.
problem Dynamic credit evaluation using streaming data.
method Neuroevolution of Augmenting Topologies (NEAT) with enhancements.
result NEAT effectively handles dynamic credit evaluation with streaming data.
Modeling bias in evaluation processes using optimization.
problem Bias in evaluation processes based on socially-salient attributes.
method Optimization-based model with two parameters: resource-information trade-off and risk-averseness.
result Characterization of distributions and effect of parameters on observed distributions.
Proposes a stability evaluation criterion for learning models using distributional perturbations.
problem Ensuring reliable deployment of learning models in out-of-sample environments.
method Uses optimal transport discrepancy with moment constraints to quantify minimal perturbation required for model deterioration.
result Validates the practical utility of the stability evaluation criterion across various real-world applications.
Machine Learning (ML) and Deep Learning (DL) innovations are being introduced at such a rapid pace that researchers are hard-pressed to analyze and study them. The complicated procedures for evaluating innovations, along with the lack of standard and efficient ways of specifying and provisioning ML/DL evaluation, is a …
This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Mark…
We explore a new way to evaluate generative models using insights from evaluation of competitive games between human players. We show experimentally that tournaments between generators and discriminators provide an effective way to evaluate generative models. We introduce two methods for summarizing tournament outcomes…
New tools evaluate and optimize conditional sequence models in bioinformatics.
problem Evaluating and optimizing conditional sequence models in bioinformatics.
method Kernel-based discrepancy measure (ACMMD) to estimate model fit and tune hyperparameters.
result Rejects the hypothesis that ProteinMPNN fits its data for various protein families and optimizes model temperature.
New method uses contrastively trained GNNs for more reliable graph model evaluation.
problem Need effective methods to evaluate Graph Generative Models.
method Use representations from contrastively trained Graph Neural Networks (GNNs) for evaluation.
result Contrastively trained GNNs provide more reliable evaluation metrics than traditional or GNN-based approaches.
ModelRadar evaluates forecasting models across multiple aspects.
problem Evaluating forecasting models using single scores hides relevant performance variations.
method ModelRadar, a framework for aspect-based evaluation of univariate time series forecasting models.
result NHITS performs best overall but its superiority varies with forecasting conditions.
New approach for prudent risk evaluation using model aggregation.
problem Risk evaluation and optimization under uncertainty.
method Model Aggregation (MA) approach based on stochastic dominance.
result Produces robust risk evaluation and distributional models.