Active Learning (AL) deals with identifying the most informative samples for labeling to reduce data annotation costs for supervised learning tasks. AL research suffers from the fact that lifts from literature generalize poorly and that only a small number of repetitions of experiments are conducted. To overcome these obstacles, we propose CDALBench, the first active learning benchmark which includes tasks in computer vision, natural language processing and tabular learning. Furthermore, by providing an efficient, greedy oracle, CDALBench can be evaluated with 50 runs for each experiment. We show, that both the cross-domain character and a large amount of repetitions are crucial for sophisticated evaluation of AL research. Concretely, we show that the superiority of specific methods varies over the different domains, making it important to evaluate Active Learning with a cross-domain benchmark. Additionally, we show that having a large amount of runs is crucial. With only conducting three runs as often done in the literature, the superiority of specific methods can strongly vary with the specific runs. This effect is so strong, that, depending on the seed, even a well-established method's performance can be significantly better and significantly worse than random for the same dataset.

Abstract--Automatic performance tuning (auto-tuning) is widely used to optimize performance-critical applications across many scientific domains by finding the best program variant among many choices. Efficient optimization algorithms are crucial for navigating the vast and complex search spaces in auto-tuning. As is well known in the context of machine learning and similar fields, hyperparameters critically shape optimization algorithm efficiency. Y et for auto-tuning frameworks, these hyperparameters are almost never tuned, and their potential performance impact has not been studied. We present a novel method for general hyperparameter tuning of optimization algorithms for auto-tuning, thus "tuning the tuner". In particular, we propose a robust statistical method for evaluating hyperparameter performance across search spaces, publish a F AIR data set and software for reproducibility, and present a simulation mode that replays previously recorded tuning data, lowering the costs of hyperparameter tuning by two orders of magnitude. We show that even limited hyperparam-eter tuning can improve auto-tuner performance by 94.8% on average, and establish that the hyperparameters themselves can be optimized efficiently with meta-strategies (with an average improvement of 204.7%), demonstrating the often overlooked hyperparameter tuning as a powerful technique for advancing auto-tuning research and practice. UTOMA TIC performance tuning, or auto-tuning, is a widely established method for optimizing the performance of applications in many scientific domains, including radio astronomy [1]-[4], image processing [5]-[7], fluid dynamics [8]-[10], and climate modeling [11]-[13]. Auto-tuning automates the process of exploring the myriad of implementation choices that arise in performance optimization, such as the number of threads, tile sizes used in loop blocking, and other code optimization parameters [14]. At the heart of the auto-tuning method is a search space of functionally-equivalent code variants that is explored by an optimization algorithm.

Active Learning (AL) deals with identifying the most informative samples for labeling to reduce data annotation costs for supervised learning tasks. AL research suffers from the fact that lifts from literature generalize poorly and that only a small number of repetitions of experiments are conducted. To overcome these obstacles, we propose \emph{CDALBench}, the first active learning benchmark which includes tasks in computer vision, natural language processing and tabular learning. Furthermore, by providing an efficient, greedy oracle, \emph{CDALBench} can be evaluated with 50 runs for each experiment. We show, that both the cross-domain character and a large amount of repetitions are crucial for sophisticated evaluation of AL research. Concretely, we show that the superiority of specific methods varies over the different domains, making it important to evaluate Active Learning with a cross-domain benchmark. Additionally, we show that having a large amount of runs is crucial. With only conducting three runs as often done in the literature, the superiority of specific methods can strongly vary with the specific runs. This effect is so strong, that, depending on the seed, even a well-established method's performance can be significantly better and significantly worse than random for the same dataset.

In this study, we explore the proactive ability of LLMs to seek user support, using text-to-SQL generation as a case study. We propose metrics to evaluate the trade-off between performance improvements and user burden, and investigate whether LLMs can determine when to request help and examine their performance with varying levels of information availability. Our experiments reveal that without external feedback, many LLMs struggle to recognize their need for additional support. Our findings highlight the importance of external signals and provide insights for future research on improving support-seeking strategies.

While recent language models have the ability to take long contexts as input, relatively little is known about how well they use longer context. We analyze the performance of language models on two tasks that require identifying relevant information in their input contexts: multi-document question answering and key-value retrieval. We find that performance can degrade significantly when changing the position of relevant information, indicating that current language models do not robustly make use of information in long input contexts. In particular, we observe that performance is often highest when relevant information occurs at the beginning or end of the input context, and significantly degrades when models must access relevant information in the middle of long contexts, even for explicitly long-context models. Our analysis provides a better understanding of how language models use their input context and provides new evaluation protocols for future long-context language models.

A major driver of AI products today is the fact that new skills emerge in language models when their parameter set and training corpora are scaled up. This phenomenon is poorly understood, and a mechanistic explanation via mathematical analysis of gradient-based training seems difficult. The current paper takes a different approach, analysing emergence using the famous (and empirical) Scaling Laws of LLMs and a simple statistical framework. Contributions include: (a) A statistical framework that relates cross-entropy loss of LLMs to competence on the basic skills that underlie language tasks. (b) Mathematical analysis showing that the Scaling Laws imply a strong form of inductive bias that allows the pre-trained model to learn very efficiently. We informally call this {\em slingshot generalization} since naively viewed it appears to give competence levels at skills that violate usual generalization theory. (c) A key example of slingshot generalization, that competence at executing tasks involving $k$-tuples of skills emerges essentially at the same scaling and same rate as competence on the elementary skills themselves.