ICML 2025 Papers

Diffusion models have emerged as a powerful framework for generative modeling, with guidance techniques playing a crucial role in enhancing sample quality. Despite their empirical success, a comprehensive theoretical understanding of the guidance effect remains limited. Existing studies only focus on case studies, where the distribution conditioned on each class is either isotropic Gaussian or supported on a one-dimensional interval with some extra conditions. How to analyze the guidance effect beyond these case studies remains an open question. Towards closing this gap, we make an attempt to analyze diffusion guidance under general data distributions. Rather than demonstrating uniform sample quality improvement, which does not hold in some distributions, we prove that guidance can improve the whole sample quality, in the sense that the ratio of bad samples (measured by the classifier probability) decreases in the presence of guidance. This aligns with the motivation of introducing guidance.

The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process called autoevaluation. We suggest efficient and statistically principled algorithms for this purpose that improve sample efficiency while remaining unbiased.

In this position paper, we observe that empirical evaluation in Generative AI is at a crisis point since traditional ML evaluation and benchmarking strategies are insufficient to meet the needs of evaluating modern GenAI models and systems. There are many reasons for this, including the fact that these models typically have nearly unbounded input and output spaces, typically do not have a well defined ground truth target, and typically exhibit strong feedback loops and prediction dependence based on context of previous model outputs. On top of these critical issues, we argue that the problems of *leakage* and *contamination* are in fact the most important and difficult issues to address for GenAI evaluations. Interestingly, the field of AI Competitions has developed effective measures and practices to combat leakage for the purpose of counteracting cheating by bad actors within a competition setting. This makes AI Competitions an especially valuable (but underutilized) resource. Now is time for the field to view AI Competitions as the gold standard for empirical rigor in GenAI evaluation, and to harness and harvest their results with according value.

In this paper, we consider the *metric $k$-center* problem in the fully dynamic setting, where we are given a metric space $(V,d)$ evolving via a sequence of point insertions and deletions and our task is to maintain a subset $S \subseteq V$ of at most $k$ points that minimizes the objective $\max_{x \in V} \min_{y \in S}d(x, y)$. We want to design our algorithm so that we minimize its *approximation ratio*, *recourse* (the number of changes it makes to the solution $S$) and *update time* (the time it takes to handle an update). We give a simple algorithm for dynamic $k$-center that maintains a $O(1)$-approximate solution with $O(1)$ amortized recourse and $\tilde O(k)$ amortized update time, *obtaining near-optimal approximation, recourse and update time simultaneously*. We obtain our result by combining a variant of the dynamic $k$-center algorithm of Bateni et al. [SODA'23] with the dynamic sparsifier of Bhattacharya et al. [NeurIPS'23].

Numerous studies have assessed the proficiency of AI systems, particularly large language models (LLMs), in facilitating everyday tasks such as email writing, question answering, and creative content generation. However, researchers face unique challenges and opportunities in leveraging LLMs for their own work, such as brainstorming research ideas, designing experiments, and writing or reviewing papers. In this study, we introduce AAAR-1.0, a benchmark dataset designed to evaluate LLM performance in three fundamental, expertise-intensive research tasks: (i) EquationInference, assessing the correctness of equations based on the contextual information in paper submissions; (ii) ExperimentDesign, designing experiments to validate research ideas and solutions; and (iii) PaperWeakness, identifying weaknesses in paper submissions. AAAR-1.0 differs from prior benchmarks in two key ways: first, it is explicitly research-oriented, with tasks requiring deep domain expertise; second, it is researcher-oriented, mirroring the primary activities that researchers engage in on a daily basis. An evaluation of both open-source and proprietary LLMs reveals their potential as well as limitations in conducting sophisticated research tasks. We will release the AAAR-1.0 and keep iterating it to new versions.

Recent research across mathematical problem solving, proof assistant programming and multimodal jailbreaking documents a striking finding: when (multimodal) language model tackle a suite of tasks with multiple attempts per task -- succeeding if any attempt is correct -- then the negative log of the average success rate scales a power law in the number of attempts. In this work, we identify an apparent puzzle: a simple mathematical calculation predicts that on each problem, the failure rate should fall exponentially with the number of attempts. We confirm this prediction empirically, raising a question: from where does aggregate polynomial scaling emerge? We then answer this question by demonstrating per-problem exponential scaling can be made consistent with aggregate polynomial scaling if the distribution of single-attempt success probabilities is heavy tailed such that a small fraction of tasks with extremely low success probabilities collectively warp the aggregate success trend into a power law - even as each problem scales exponentially on its own. We further demonstrate that this distributional perspective explains previously observed deviations from power law scaling, and provides a simple method for forecasting the power law exponent with an order of magnitude lower relative error, or equivalently, ${\sim}2-4$ orders of magnitude less inference compute. Overall, our work contributes to a better understanding of how neural language model performance improves with scaling inference compute and the development of scaling-predictable evaluations of (multimodal) language models.

Recent Large Language Models (LLMs) have reported high accuracy on reasoning benchmarks. However, it is still unclear whether the observed results arise from true “reasoning” or from statistical recall of the training set. Inspired by the ladder of causation (Pearl, 2009) and its three levels (associations, interventions and counterfactuals), this paper introduces RE-IMAGINE: a framework to characterize a hierarchy of reasoning ability in LLMs, alongside an automated pipeline to generate problem variations at different levels of the hierarchy. By altering problems in an intermediate symbolic representation, RE-IMAGINE generates arbitrarily many problems that are not solvable using memorization alone. Moreover, the framework is general and can work across reasoning domains, including math, code, and logic. We demonstrate our framework on four widely-used benchmarks to evaluate several families of LLMs, and observe reductions in performance when the models are queried with problem variations. These assessments indicate a degree of reliance on statistical recall for past performance, and open the door to further research targeting skills across the reasoning hierarchy.

We study the classic correlation clustering problem. Given $n$ objects and a complete labeling of the object-pairs as either “similar” or “dissimilar”, the goal is to partition the objects into arbitrarily many clusters while minimizing disagreements with the labels. A classic Pivot algorithm for this problem, due to [Ailon et al STOC'05], obtains a 3-approximation for this problem. Over the years, this algorithm has been successfully implemented in various settings. The downside of the Pivot algorithm is that the approximation analysis of 3 is tight for it. While better approximations have been achieved in some settings, these algorithms are often hard to implement in various settings. For example, [Behnezhad et al FOCS19] showed that the output of Pivot can be maintained in polylog time per update in a dynamic setting, a bound that was improved to constant by [Dalirrooyfard et al ICML'24]. But obtaining a better approximation remains open. In this paper, we present Modified Pivot, an algorithm that locally improves the output of Pivot. Our Modified Pivot algorithm can be implemented just as efficiently as Pivot in various settings. Our experiments show that the output of Modified Pivot on average makes less than 77\% of the mistakes made by Pivot. More surprisingly, we prove theoretically that Modified Pivot has approximation ratio $3-\epsilon_0$ for some absolute constant $\epsilon_0 > 0$. This, e.g., leads to a better than 3 approximation in the dynamic setting in polylog time, improving the 3-approximation obtained by [Behnezhad et al FOCS'19] and [Dalirrooyfard et al ICML'24].

Standard conformal prediction ensures marginal coverage but consistently undercovers underrepresented groups, limiting its reliability for fair uncertainty quantification. Group fairness requires prediction sets to achieve a user-specified coverage level within each protected group. While group-wise conformal inference meets this requirement, it often produces excessively wide prediction sets due to limited sample sizes in underrepresented groups, highlighting a fundamental tradeoff between fairness and efficiency. To bridge this gap, we introduce Surrogate-Assisted Group-Clustered Conformal Inference (SAGCCI), a framework that improves efficiency through two key innovations: (1) clustering protected groups with similar conformal score distributions to enhance precision while maintaining fairness, and (2) deriving an efficient influence function that optimally integrates surrogate outcomes to construct tighter prediction sets. Theoretically, SAGCCI guarantees approximate group-conditional coverage in a doubly robust manner under mild convergence conditions, enabling flexible nuisance model estimation. Empirically, through simulations and an analysis of the phase 3 Moderna COVE COVID-19 vaccine trial, we demonstrate that SAGCCI outperforms existing methods, producing narrower prediction sets while maintaining valid group-conditional coverage, effectively balancing fairness and efficiency in uncertainty quantification.

We study contextual bandits with general constraints, where a learner observes contexts and aims to maximize cumulative rewards while satisfying a wide range of general constraints. We introduce the Optimistic$^3$ framework, a novel learning and decision-making approach that integrates optimistic design into parameter learning, primal decision, and dual violation adaptation (i.e., triple-optimism), combined with an efficient primal-dual architecture. Optimistic$^3$ achieves $\tilde{O}(\sqrt{T})$ regret and constraint violation for contextual bandits with general constraints. This framework not only outperforms the state-of-the-art results that achieve $\tilde{O}(T^{\frac{3}{4}})$ guarantees when Slater's condition does not hold but also improves on previous results that achieve $\tilde{O}(\sqrt{T}/\delta)$ when Slater's condition holds ($\delta$ denotes the Slater's condition parameter), offering a $O(1/\delta)$ improvement. Note this improvement is significant because $\delta$ can be arbitrarily small when constraints are particularly challenging. Moreover, we show that Optimistic$^3$ can be extended to classical multi-armed bandits with both stochastic and adversarial constraints, recovering the best-of-both-worlds guarantee established in the state-of-the-art works, but with significantly less computational overhead.

As AI systems continue to evolve, their rigorous evaluation becomes crucial for their development and deployment. Researchers have constructed various large-scale benchmarks to determine their capabilities, typically against a gold-standard test set and report metrics averaged across all items. However, this static evaluation paradigm increasingly shows its limitations, including high evaluation costs, data contamination, and the impact of low-quality or erroneous items on evaluation reliability and efficiency. In this Position, drawing from human psychometrics, we discuss a paradigm shift from static evaluation methods to adaptive testing. This involves estimating the characteristics or value of each test item in the benchmark, and tailoring each model's evaluation instead of relying on a fixed test set. This paradigm provides robust ability estimation, uncovering the latent traits underlying a model’s observed scores. This position paper analyze the current possibilities, prospects, and reasons for adopting psychometrics in AI evaluation. We argue that *psychometrics, a theory originating in the 20th century for human assessment, could be a powerful solution to the challenges in today's AI evaluations*.

Data contamination—the accidental consumption of evaluation examples within the pre-training data—can undermine the validity of evaluation benchmarks. In this paper, we present a rigorous analysis of the effects of contamination on language models at 1B and 8B scales on the machine translation task. Starting from a carefully decontaminated train-test split, we systematically introduce contamination at various stages, scales, and data formats to isolate its effect and measure its impact on performance metrics. Our experiments reveal that contamination with both source and target substantially inflates BLEU scores, and this inflation is 2.5 times larger (up to 30 BLEU points) for 8B compared to 1B models. In contrast, source-only and target-only contamination generally produce smaller, less consistent over-estimations. Finally, we study how the temporal distribution and frequency of contaminated samples influence performance over-estimation across languages with varying degrees of data resources.

Diversity has been one of the most crucial factors on the design of adversarial ensemble methods. This work focuses on the fundamental problems: How to define the diversity for the adversarial ensemble, and how to correlate with algorithmic performance. We first show that it is an NP-Hard problem to precisely calculate the diversity of two networks in adversarial ensemble learning, which makes it different from prior diversity analysis. We present the first diversity decomposition under the first-order approximation for the adversarial ensemble learning. Specifically, the adversarial ensemble loss can be decomposed into average of individual adversarial losses, gradient diversity, prediction diversity and cross diversity. Hence, it is not sufficient to merely consider the gradient diversity on the characterization of diversity as in previous adversarial ensemble methods. We present diversity decomposition for classification with cross-entropy loss similarly. Based on the theoretical analysis, we develop new ensemble method via orthogonal adversarial predictions to simultaneously improve gradient diversity and cross diversity. We finally conduct experiments to validate the effectiveness of our method.

The rapid evolution of Large Language Models (LLMs) has outpaced the development of model evaluation, highlighting the need for continuous curation of new, challenging benchmarks. However, manual curation of high-quality, human-aligned benchmarks is expensive and time-consuming. To address this, we introduce BenchBuilder, an automated pipeline that leverages LLMs to curate high-quality, open-ended prompts from large, crowd-sourced datasets, enabling continuous benchmark updates without human in the loop. We apply BenchBuilder to datasets such as Chatbot Arena and WildChat-1M, extracting challenging prompts and utilizing LLM-as-a-Judge for automatic model evaluation. To validate benchmark quality, we propose new metrics to measure a benchmark’s alignment with human preferences and ability to separate models. We release Arena-Hard-Auto, a benchmark consisting 500 challenging prompts curated by BenchBuilder. Arena-Hard-Auto provides 3x higher separation of model performances compared to MT-Bench and achieves 98.6% correlation with human preference rankings, all at a cost of $20. Our work sets a new framework for the scalable curation of automated benchmarks from extensive data.

Feature importance metrics are critical for interpreting machine learning models and understanding the relevance of individual features. However, real-world data often exhibit missingness, thereby complicating how feature importance should be evaluated. We introduce the distinction between two evaluation frameworks under missing data: (1) feature importance under the full data, as if every feature had been fully measured, and (2) feature importance under the observed data, where missingness is governed by the current measurement policy. While the full data perspective offers insights into the data generating process, it often relies on unrealistic assumptions and cannot guide decisions when missingness persists at model deployment. Since neither framework directly informs improvements in data collection, we additionally introduce the feature measurement importance gradient (FMIG), a novel, model-agnostic metric that identifies features that should be measured more frequently to enhance predictive performance. Using synthetic data, we illustrate key differences between these metrics and the risks of conflating them.

Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but also continual, post-deployment monitoring to quickly detect and address any unsafe behavior. Methods for nonparametric sequential testing---especially conformal test martingales (CTMs) and anytime-valid inference---offer promising tools for this monitoring task. However, existing approaches are restricted to monitoring limited hypothesis classes or ``alarm criteria'' (e.g., detecting data shifts that violate certain exchangeability or IID assumptions), do not allow for online adaptation in response to shifts, and/or cannot diagnose the cause of degradation or alarm. In this paper, we address these limitations by proposing a weighted generalization of conformal test martingales (WCTMs), which lay a theoretical foundation for online monitoring for any unexpected changepoints in the data distribution while controlling false-alarms. For practical applications, we propose specific WCTM algorithms that adapt online to mild covariate shifts (in the marginal input distribution), quickly detect harmful shifts, and diagnose those harmful shifts as concept shifts (in the conditional label distribution) or extreme (out-of-support) covariate shifts that cannot be easily adapted to. On real-world datasets, we demonstrate improved performance relative to state-of-the-art baselines.

Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be as *complex* as we think, as the way they are built distorts our perception of progress in this field. For example, we find that in these benchmarks most queries (up to 98% for some query types) can be reduced to simpler problems, e.g., link prediction, where only one link needs to be predicted. The performance of state-of-the-art CQA models decreses significantly when such models are evaluated on queries that cannot be reduced to easier types. Thus, we propose a set of more challenging benchmarks composed of queries that *require* models to reason over multiple hops and better reflect the construction of real-world KGs. In a systematic empirical investigation, the new benchmarks show that current methods leave much to be desired from current CQA methods.

Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating system suffers from the inevitable instability problem due to ranking inconsistency and the lack of attention to the varying abilities of annotators. In this paper, we introduce a novel stable arena framework to address these issues by enhancing the ELO Rating System. Specifically, we replace the iterative update method with a Maximum Likelihood Estimation (MLE) approach, m-ELO, and provide theoretical proof of the consistency and stability of the MLE approach for model ranking. Additionally, we proposed the am-ELO, which modify the Elo Rating’s probability function to incorporate annotator abilities, enabling the simultaneous estimation of model scores and annotator reliability. Experiments demonstrate that this method ensures stability, proving that this framework offers a more robust, accurate, and stable evaluation method for LLMs.

Large language models (LLMs) are widely adopted to generate synthetic datasets for various natural language processing (NLP) tasks, such as text classification and summarization. However, accurately measuring the diversity of these synthetic datasets—an aspect crucial for robust model performance—remains a significant challenge. In this paper, we introduce DCScore, a novel method for measuring synthetic dataset diversity from a classification perspective. Specifically, DCScore formulates diversity evaluation as a sample classification task, leveraging mutual relationships among samples. We further provide theoretical verification of the diversity-related axioms satisfied by DCScore, highlighting its role as a principled diversity evaluation method. Experimental results on synthetic datasets reveal that DCScore enjoys a stronger correlation with multiple diversity pseudo-truths of evaluated datasets, underscoring its effectiveness. Moreover, both empirical and theoretical evidence demonstrate that DCScore substantially reduces computational costs compared to existing methods. Code is available at: https://github.com/bluewhalelab/dcscore.