相关论文: GRACE: A Granular Benchmark for Evaluating Model C…

This paper provides both an introduction to and a detailed overview of the principles and practice of classifier calibration. A well-calibrated classifier correctly quantifies the level of uncertainty or confidence associated with its…

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The significance of calibration lies in its critical role in…

Today, AI is being increasingly used to help human experts make decisions in high-stakes scenarios. In these scenarios, full automation is often undesirable, not only due to the significance of the outcome, but also because human experts…

We consider the problem of calibrating an imperfect computer model using experimental data. To compensate the misspecification of the computer model and make more accurate predictions, a discrepancy function is often included and modeled…

Advanced test-time computing strategies are essential for scaling reasoning models, but their effectiveness is capped by the models' poor self-evaluation. We propose a pairwise Explanatory Verifier, trained via reinforcement learning…

Automated scoring of student work at scale requires balancing accuracy against cost and latency. In "cascade" systems, small language models (LMs) handle easier scoring tasks while escalating harder ones to larger LMs -- but the challenge…

Large Language Models (LLMs) show remarkable proficiency in natural language tasks, yet their frequent overconfidence-misalignment between predicted confidence and true correctness-poses significant risks in critical decision-making…

Grammatical Error Correction (GEC) faces a critical challenge concerning explainability, notably when GEC systems are designed for language learners. Existing research predominantly focuses on explaining grammatical errors extracted in…

Existing metrics for assessing question generation not only require costly human reference but also fail to take into account the input context of generation, rendering the lack of deep understanding of the relevance between the generated…

Building accurate language models that capture meaningful long-term dependencies is a core challenge in natural language processing. Towards this end, we present a calibration-based approach to measure long-term discrepancies between a…

Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…

Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit biases in evaluation and often struggle to generate coherent…

Large language models (LLMs) are increasingly used as automated evaluators, yet prior works demonstrate that these LLM judges often lack consistency in scoring when the prompt is altered. However, the effect of the grading scale itself…

Fine-tuning approaches for Vision-Language Models (VLMs) face a critical three-way trade-off between In-Distribution (ID) accuracy, Out-of-Distribution (OOD) generalization, and adversarial robustness. Existing robust fine-tuning strategies…

In safety-critical applications a probabilistic model is usually required to be calibrated, i.e., to capture the uncertainty of its predictions accurately. In multi-class classification, calibration of the most confident predictions only is…

How should we compare the capabilities of language models (LMs) and humans? I draw inspiration from comparative psychology to highlight some challenges. In particular, I consider a case study: processing of recursively nested grammatical…

While large language models (LLMs) are generally considered proficient in generating language, how similar their language usage is to that of humans remains understudied. In this paper, we test whether models exhibit linguistic convergence,…

Language models (LMs) are increasingly used to simulate human-like responses in scenarios where accurately mimicking a population's behavior can guide decision-making, such as in developing educational materials and designing public…

Typical evaluations of Large Language Models (LLMs) report a single metric per dataset, often representing the model's best-case performance under carefully selected settings. Unfortunately, this approach overlooks model robustness and…

As AI becomes more integral in our lives, the need for transparency and responsibility grows. While natural language explanations (NLEs) are vital for clarifying the reasoning behind AI decisions, evaluating them through human judgments is…