English
Related papers

Related papers: Towards Zero-Shot and Few-Shot Table Question Answ…

200 papers

Large language models, particularly GPT-3, are able to produce high quality summaries of general domain news articles in few- and zero-shot settings. However, it is unclear if such models are similarly capable in more specialized,…

Computation and Language · Computer Science 2023-05-12 Chantal Shaib , Millicent L. Li , Sebastian Joseph , Iain J. Marshall , Junyi Jessy Li , Byron C. Wallace

Large language models like GPT-4 exhibit emergent capabilities across general-purpose tasks, such as basic arithmetic, when trained on extensive text data, even though these tasks are not explicitly encoded by the unsupervised, next-token…

Machine Learning · Computer Science 2023-07-10 Nayoung Lee , Kartik Sreenivasan , Jason D. Lee , Kangwook Lee , Dimitris Papailiopoulos

With increasing scale, large language models demonstrate both quantitative improvement and new qualitative capabilities, especially as zero-shot learners, like GPT-3. However, these results rely heavily on delicate prompt design and large…

Computation and Language · Computer Science 2022-12-21 Jingjing Xu , Qingxiu Dong , Hongyi Liu , Lei Li

Deep graph generative modeling has gained enormous attraction in recent years due to its impressive ability to directly learn the underlying hidden graph distribution. Despite their initial success, these techniques, like much of the…

Machine Learning · Computer Science 2023-12-15 Sahil Manchanda , Shubham Gupta , Sayan Ranu , Srikanta Bedathur

Efficiently extracting data from tables in the scientific literature is pivotal for building large-scale databases. However, the tables reported in materials science papers exist in highly diverse forms; thus, rule-based extractions are an…

Few-shot Knowledge Graph (KG) Relational Reasoning aims to predict unseen triplets (i.e., query triplets) for rare relations in KGs, given only several triplets of these relations as references (i.e., support triplets). This task has gained…

Computation and Language · Computer Science 2024-06-25 Haochen Liu , Song Wang , Chen Chen , Jundong Li

Statutory reasoning is the task of reasoning with facts and statutes, which are rules written in natural language by a legislature. It is a basic legal skill. In this paper we explore the capabilities of the most capable GPT-3 model,…

Computation and Language · Computer Science 2023-05-12 Andrew Blair-Stanek , Nils Holzenberger , Benjamin Van Durme

This study investigates the application of large language models (LLMs), specifically GPT-3.5 and GPT-4, with Chain-of-Though (CoT) in the automatic scoring of student-written responses to science assessments. We focused on overcoming the…

Computation and Language · Computer Science 2024-02-20 Gyeong-Geon Lee , Ehsan Latif , Xuansheng Wu , Ninghao Liu , Xiaoming Zhai

We assessed the performance of commercial Large Language Models (LLMs) GPT-3.5-Turbo and GPT-4 on tasks from the 2023 BioASQ challenge. In Task 11b Phase B, which is focused on answer generation, both models demonstrated competitive…

Computation and Language · Computer Science 2023-07-25 Samy Ateia , Udo Kruschwitz

In-context learning of GPT-like models has been recognized as fragile across different hand-crafted templates, and demonstration permutations. In this work, we propose prototypical calibration to adaptively learn a more robust decision…

Computation and Language · Computer Science 2022-10-06 Zhixiong Han , Yaru Hao , Li Dong , Yutao Sun , Furu Wei

This paper provides an introductory survey to GPT-3. We cover some of the historical development behind this technology, some of the key features of GPT-3, and discuss the machine learning model and the datasets used. We survey both…

Computation and Language · Computer Science 2022-12-05 Mingyu Zong , Bhaskar Krishnamachari

The task of triplet extraction aims to extract pairs of entities and their corresponding relations from unstructured text. Most existing methods train an extraction model on training data involving specific target relations, and are…

Computation and Language · Computer Science 2023-09-21 Bosung Kim , Hayate Iso , Nikita Bhutani , Estevam Hruschka , Ndapa Nakashole , Tom Mitchell

Neural-based end-to-end approaches to natural language generation (NLG) from structured data or knowledge are data-hungry, making their adoption for real-world applications difficult with limited data. In this work, we propose the new task…

Computation and Language · Computer Science 2020-04-21 Zhiyu Chen , Harini Eavani , Wenhu Chen , Yinyin Liu , William Yang Wang

Radiology, radiation oncology, and medical physics require decision-making that integrates medical images, textual reports, and quantitative data under high-stakes conditions. With the introduction of GPT-5, it is critical to assess whether…

Image and Video Processing · Electrical Eng. & Systems 2025-08-20 Mingzhe Hu , Zach Eidex , Shansong Wang , Mojtaba Safari , Qiang Li , Xiaofeng Yang

This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without training data. Queried with a zero-shot question-answering prompt, GPT-3 can identify the hero, villain, and victim…

Computation and Language · Computer Science 2022-05-18 Dominik Stammbach , Maria Antoniak , Elliott Ash

The task of learning from only a few examples (called a few-shot setting) is of key importance and relevance to a real-world setting. For question answering (QA), the current state-of-the-art pre-trained models typically need fine-tuning on…

Computation and Language · Computer Science 2021-10-13 Rakesh Chada , Pradeep Natarajan

Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields…

Computation and Language · Computer Science 2021-10-05 Timo Schick , Hinrich Schütze

Generative Pre-trained Transformers (GPTs) have recently been scaled to unprecedented sizes in the history of machine learning. These models, solely trained on the language modeling objective, have been shown to exhibit outstanding few-shot…

Computation and Language · Computer Science 2021-08-31 Jordi Armengol-Estapé , Ona de Gibert Bonet , Maite Melero

Recent advances in few-shot question answering (QA) mostly rely on the power of pre-trained large language models (LLMs) and fine-tuning in specific settings. Although the pre-training stage has already equipped LLMs with powerful reasoning…

Computation and Language · Computer Science 2024-05-29 Xiusi Chen , Jyun-Yu Jiang , Wei-Cheng Chang , Cho-Jui Hsieh , Hsiang-Fu Yu , Wei Wang

Learning with few labeled tabular samples is often an essential requirement for industrial machine learning applications as varieties of tabular data suffer from high annotation costs or have difficulties in collecting new samples for novel…

Machine Learning · Computer Science 2023-03-03 Jaehyun Nam , Jihoon Tack , Kyungmin Lee , Hankook Lee , Jinwoo Shin