Related papers: UQ: Assessing Language Models on Unsolved Question…

Can AI make progress on important, unsolved mathematical problems? Large language models are now capable of sophisticated mathematical and scientific reasoning, but whether they can perform novel research is still widely debated and…

As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the…

Large Language Models (LLMs) have made significant strides in mathematical reasoning, underscoring the need for a comprehensive and fair evaluation of their capabilities. However, existing benchmarks often fall short, either lacking…

The Best Estimate plus Uncertainty (BEPU) approach for nuclear systems modeling and simulation requires that the prediction uncertainty must be quantified in order to prove that the investigated design stays within acceptance criteria. A…

AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attributes and for comparing model performance, tracking…

Large language models (LLMs) show remarkable promise for democratizing automated reasoning by generating formal specifications. However, a fundamental tension exists: LLMs are probabilistic, while formal verification demands deterministic…

As machine learning (ML) models are increasingly deployed in high-stakes domains, trustworthy uncertainty quantification (UQ) is critical for ensuring the safety and reliability of these models. Traditional UQ methods rely on specifying a…

Rigorous and reproducible evaluation is critical for assessing the state of the art and for guiding scientific advances in Artificial Intelligence. Evaluation is challenging in practice due to several reasons, including benchmark…

Large language models (LLMs) excel at solving problems with clear and complete statements, but often struggle with nuanced environments or interactive tasks which are common in most real-world scenarios. This highlights the critical need…

Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning research community has increasingly turned toward empirical…

Recent multimodal large language models (MLLMs) show strong capabilities in visual-language reasoning, yet their performance on ultra-high-resolution imagery remains largely unexplored. Existing visual question answering (VQA) benchmarks…

Hallucinations are a persistent problem with Large Language Models (LLMs). As these models become increasingly used in high-stakes domains, such as healthcare and finance, the need for effective hallucination detection is crucial. To this…

Cultural AI benchmarks often rely on implicit assumptions about measured constructs, leading to vague formulations with poor validity and unclear interrelations. We propose exposing these assumptions using explicit cognitive models…

Users typically engage with LLMs interactively, yet most existing benchmarks evaluate them in a static, single-turn format, posing reliability concerns in interactive scenarios. We identify a key obstacle towards reliability: LLMs are…

The current evaluation of mathematical skills in LLMs is limited, as existing benchmarks are either relatively small, primarily focus on elementary and high-school problems, or lack diversity in topics. Additionally, the inclusion of visual…

Despite warnings that LLMs can make mistakes, users often develop inappropriate trust and accept incorrect answers without critical evaluation. Uncertainty quantification (UQ), displaying LLMs' confidence, has emerged as a promising…

There is a growing need to gain insight into language model capabilities that relate to sensitive topics, such as bioterrorism or cyberwarfare. However, traditional open source benchmarks are not fit for the task, due to the associated…

Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic "I don't know'', failing to distinguish input-level ambiguity (data uncertainty) from capability…

There is a lack of benchmarks for evaluating large language models (LLMs) in long-form medical question answering (QA). Most existing medical QA evaluation benchmarks focus on automatic metrics and multiple-choice questions. While valuable,…

Quantifying uncertainty of machine learning model predictions is essential for reliable decision-making, especially in safety-critical applications. Recently, uncertainty quantification (UQ) theory has advanced significantly, building on a…