相关论文: The Evaluation Trap: Benchmark Design as Theoretic…

In recent years, with the rapid development of the depth and breadth of large language models' capabilities, various corresponding evaluation benchmarks have been emerging in increasing numbers. As a quantitative assessment tool for model…

Despite significant progress in designing powerful adversarial evasion attacks for robustness verification, the evaluation of these methods often remains inconsistent and unreliable. Many assessments rely on mismatched models, unverified…

Recent trends in planning research have led to empirical comparison becoming commonplace. The field has started to settle into a methodology for such comparisons, which for obvious practical reasons requires running a subset of planners on…

The proliferation of generative AI tools has rendered traditional modular assessments in computing and data-centric education increasingly ineffective, creating a disconnect between academic evaluation and authentic skill measurement. This…

This position paper argues that standardized item-level benchmark data should become the default infrastructure for AI evaluation. Current evaluations suffer from underspecified item selection, construct misalignment, and poor…

AI safety benchmarks are pivotal for safety in advanced AI systems; however, they have significant technical, epistemic, and sociotechnical shortcomings. We present a review of 210 safety benchmarks that maps out common challenges in safety…

Recent research in explainability has given rise to numerous post-hoc attribution methods aimed at enhancing our comprehension of the outputs of black-box machine learning models. However, evaluating the quality of explanations lacks a…

Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for…

Conducting contamination-free evaluation of mathematical capabilities can be difficult for two reasons: models may memorize a test set once it is made public, and current mathematical benchmarks are prone to overfitting due to having…

We introduce benchmark signatures to characterize the capacity demands of LLM benchmarks and their overlaps. Signatures are sets of salient tokens from in-the-wild corpora whose model token perplexity, reflecting training exposure, predicts…

Evaluation is the baton for the development of large language models. Current evaluations typically employ a single-item assessment paradigm for each atomic test objective, which struggles to discern whether a model genuinely possesses the…

Evaluating the efficiency of human-AI interactions is challenging, including subjective and objective quality aspects. With the focus on the human experience of the explanations, evaluations of explanation methods have become mostly…

Artificial intelligence systems are increasingly deployed in biomedical research. However, current evaluation frameworks may inadequately assess their effectiveness as research collaborators. This rapid review examines benchmarking…

In the era of increasingly complex AI models for time series forecasting, progress is often measured by marginal improvements on benchmark leaderboards. However, this approach suffers from a fundamental flaw: standard evaluation metrics…

Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended…

As a research community, we are still lacking a systematic understanding of the progress on adversarial robustness which often makes it hard to identify the most promising ideas in training robust models. A key challenge in benchmarking…

The peer review process is crucial for ensuring the quality and reliability of scholarly work, yet assigning suitable reviewers remains a significant challenge. Traditional manual methods are labor-intensive and often ineffective, leading…

A `state of the art' model A surpasses humans in a benchmark B, but fails on similar benchmarks C, D, and E. What does B have that the other benchmarks do not? Recent research provides the answer: spurious bias. However, developing A to…

Reasoning benchmarks such as the Abstraction and Reasoning Corpus (ARC) and ARC-AGI are widely used to assess progress in artificial intelligence and are often interpreted as probes of core, so-called ``fluid'' reasoning abilities. Despite…