相关论文: On the Difficulty of Evaluating Baselines: A Study…

We conduct a systematic audit of three widely used reasoning benchmarks, SocialIQa, FauxPas-EAI, and ToMi, and uncover pervasive flaws in both benchmark items and evaluation methodology. Using five LLMs (GPT-{3, 3.5, 4, o1}, and LLaMA 3.1)…

Yes, and no. We ask whether recent progress on the ImageNet classification benchmark continues to represent meaningful generalization, or whether the community has started to overfit to the idiosyncrasies of its labeling procedure. We…

Several benchmarks have been built with heavy investment in resources to track our progress in NLP. Thousands of papers published in response to those benchmarks have competed to top leaderboards, with models often surpassing human…

Neural networks can fail when the data contains spurious correlations. To understand this phenomenon, researchers have proposed numerous spurious correlations benchmarks upon which to evaluate mitigation methods. However, we observe that…

While other areas of machine learning have seen more and more automation, designing a high-performing recommender system still requires a high level of human effort. Furthermore, recent work has shown that modern recommender system…

Graph-structured data is prevalent in domains such as social networks, financial transactions, brain networks, and protein interactions. As a result, the research community has produced new databases and analytics engines to process such…

Recommender systems are indispensable because they influence our day-to-day behavior and decisions by giving us personalized suggestions. Services like Kindle, Youtube, and Netflix depend heavily on the performance of their recommender…

Recommender systems are important and powerful tools for various personalized services. Traditionally, these systems use data mining and machine learning techniques to make recommendations based on correlations found in the data. However,…

Recommender systems play a critical role in enhancing user experience by providing personalized suggestions based on user preferences. Traditional approaches often rely on explicit numerical ratings or assume access to fully ranked lists of…

Cloud benchmarks suffer from performance fluctuations caused by resource contention, network latency, hardware heterogeneity, and other factors along with decisions taken in the benchmark design. In particular, the sampling strategy of…

Confronted with the challenge of identifying the most suitable metric to validate the merits of newly proposed models, the decision-making process is anything but straightforward. Given that comparing rankings introduces its own set of…

Ranking entities such as algorithms, devices, methods, or models based on their performances, while accounting for application-specific preferences, is a challenge. To address this challenge, we establish the foundations of a universal…

In this thesis, I refine our understanding as to what conclusions we can reach from coreference-based evaluations by expanding existing evaluation practices and considering the extent to which evaluation results are either converging or…

Benchmarks establish a standardized evaluation framework to systematically assess the performance of large language models (LLMs), facilitating objective comparisons and driving advancements in the field. However, existing benchmarks fail…

When deploying large language models (LLMs), it is important to ensure that these models are not only capable, but also reliable. Many benchmarks have been created to track LLMs' growing capabilities, however there has been no similar focus…

NLP models have progressed drastically in recent years, according to numerous datasets proposed to evaluate performance. Questions remain, however, about how particular dataset design choices may impact the conclusions we draw about model…

Reranking methods in machine translation aim to close the gap between common evaluation metrics (e.g. BLEU) and maximum likelihood learning and decoding algorithms. Prior works address this challenge by training models to rerank beam search…

The emergent phenomena of large foundation models have revolutionized natural language processing. However, evaluating these models presents significant challenges due to their size, capabilities, and deployment across diverse applications.…

We increasingly depend on a variety of data-driven algorithmic systems to assist us in many aspects of life. Search engines and recommender systems amongst others are used as sources of information and to help us in making all sort of…

Despite huge successes on a wide range of tasks, neural networks are known to sometimes struggle to generalise to unseen data. Many approaches have been proposed over the years to promote the generalisation ability of neural networks,…