English
Related papers

Related papers: Growth Patterns of Inference

200 papers

We conduct a large empirical evaluation to investigate the landscape of distributional robustness in question answering. Our investigation spans over 350 models and 16 question answering datasets, including a diverse set of architectures,…

Computation and Language · Computer Science 2022-10-25 Anas Awadalla , Mitchell Wortsman , Gabriel Ilharco , Sewon Min , Ian Magnusson , Hannaneh Hajishirzi , Ludwig Schmidt

Large language models leverage both parametric knowledge acquired during pretraining and in-context knowledge provided at inference time. Crucially, when these sources conflict, models arbitrate based on their internal confidence,…

Computation and Language · Computer Science 2026-04-21 Minsung Kim , Dong-Kyum Kim , Jea Kwon , Nakyeong Yang , Kyomin Jung , Meeyoung Cha

Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes: either depending on costly interventional signals or partial ground truth as strong priors, or adopting purely data…

Machine Learning · Computer Science 2026-03-24 Wenbo Xu , Yue He , Yunhai Wang , Xingxuan Zhang , Kun Kuang , Yueguo Chen , Peng Cui

This work investigates the ``small-vs-large gap'', where repeating on fewer samples can lead to compute saving during training compared to using a larger dataset. This is observed across algorithmic tasks, architectures and optimizers and…

Machine Learning · Computer Science 2026-05-21 Jingwen Liu , Ezra Edelman , Surbhi Goel , Bingbin Liu

Retrieval-augmented generation models augment knowledge encoded in a language model by providing additional relevant external knowledge (context) during generation. Although it has been shown that the quantity and quality of context impact…

Computation and Language · Computer Science 2024-03-22 Kosuke Akimoto , Kunihiro Takeoka , Masafumi Oyamada

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Computation and Language · Computer Science 2023-12-25 Afra Amini , Massimiliano Ciaramita

Supervised classification methods often assume the train and test data distributions are the same and that all classes in the test set are present in the training set. However, deployed classifiers often require the ability to recognize…

Computer Vision and Pattern Recognition · Computer Science 2021-01-27 Ryne Roady , Tyler L. Hayes , Ronald Kemker , Ayesha Gonzales , Christopher Kanan

Datasets for training object recognition systems are steadily increasing in size. This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model…

Computer Vision and Pattern Recognition · Computer Science 2015-03-06 Xiangxin Zhu , Carl Vondrick , Charless Fowlkes , Deva Ramanan

Large language models have become a powerful method for feature augmentation in recommendation systems. However, existing approaches relying on quick inference often suffer from incomplete feature coverage and insufficient specificity in…

Information Retrieval · Computer Science 2025-02-25 Weihao Liu , Zhaocheng Du , Haiyuan Zhao , Wenbo Zhang , Xiaoyan Zhao , Gang Wang , Zhenhua Dong , Jun Xu

The performance of enumerating all solutions to an instance of Langford's Problem is sensitive to the model and the search strategy. In this paper we compare the performance of a large variety of models, all derived from two base…

Artificial Intelligence · Computer Science 2018-08-30 Özgür Akgün , Ian Miguel

Causal Bayesian networks have become a powerful technology for reasoning under uncertainty in areas that require transparency and explainability, by relying on causal assumptions that enable us to simulate hypothetical interventions. The…

Artificial Intelligence · Computer Science 2023-03-14 Anthony C. Constantinou , Zhigao Guo , Neville K. Kitson

Although BERT-based ranking models have been commonly used in commercial search engines, they are usually time-consuming for online ranking tasks. Knowledge distillation, which aims at learning a smaller model with comparable performance to…

Information Retrieval · Computer Science 2023-02-09 Xubo Qin , Xiyuan Liu , Xiongfeng Zheng , Jie Liu , Yutao Zhu

Several tasks in information retrieval (IR) rely on assumptions regarding the distribution of some property (such as term frequency) in the data being processed. This thesis argues that such distributional assumptions can lead to incorrect…

Information Retrieval · Computer Science 2019-04-02 Casper Petersen

Deep learning techniques have demonstrated significant capacity in modeling some of the most challenging real world problems of high complexity. Despite the popularity of deep models, we still strive to better understand the underlying…

Computer Vision and Pattern Recognition · Computer Science 2016-07-11 Yu Zhong , Gil Ettinger

Decision Tree (DT) Learning is a fundamental problem in Interpretable Machine Learning, yet it poses a formidable optimisation challenge. Practical algorithms have recently emerged, primarily leveraging Dynamic Programming and Branch &…

Machine Learning · Computer Science 2025-05-13 Ayman Chaouki , Jesse Read , Albert Bifet

This thesis details a class of partial orders on the space of probability distributions and the space of density operators which capture the idea of information content. Some links to domain theory and computational linguistics are also…

Logic in Computer Science · Computer Science 2017-01-25 John van de Wetering

Computer-aided design of molecules has the potential to disrupt the field of drug and material discovery. Machine learning, and deep learning, in particular, have been topics where the field has been developing at a rapid pace.…

Machine Learning · Computer Science 2022-08-08 Luca A. Thiede , Mario Krenn , AkshatKumar Nigam , Alan Aspuru-Guzik

We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well…

Computation and Language · Computer Science 2020-10-07 Xusen Yin , Ralph Weischedel , Jonathan May

Model explainability is crucial for human users to be able to interpret how a proposed classifier assigns labels to data based on its feature values. We study generalized linear models constructed using sets of feature value rules, which…

Machine Learning · Statistics 2023-11-06 Sanjeeb Dash , Soumyadip Ghosh , Joao Goncalves , Mark S. Squillante

Nowadays, cooperative multi-agent systems are used to learn how to achieve goals in large-scale dynamic environments. However, learning in these environments is challenging: from the effect of search space size on learning time to…

Multiagent Systems · Computer Science 2022-01-19 Mahnoosh Mahdavimoghaddam , Amin Nikanjam , Monireh Abdoos