Hallucination detection and hallucination mitigation: An investigation

J Luo, T Li, D Wu, M Jenkin, S Liu, G Dudek - arxiv preprint arxiv …, 2024‏ - arxiv.org
Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved
remarkable successes over the last two years in a range of different applications. In spite of …

Multimodal pretraining, adaptation, and generation for recommendation: A survey

Q Liu, J Zhu, Y Yang, Q Dai, Z Du, XM Wu… - Proceedings of the 30th …, 2024‏ - dl.acm.org
Personalized recommendation serves as a ubiquitous channel for users to discover
information tailored to their interests. However, traditional recommendation models primarily …

PRIMERA: Pyramid-based masked sentence pre-training for multi-document summarization

W **ao, I Beltagy, G Carenini, A Cohan - arxiv preprint arxiv:2110.08499, 2021‏ - arxiv.org
We introduce PRIMERA, a pre-trained model for multi-document representation with a focus
on summarization that reduces the need for dataset-specific architectures and large …

Fill in the BLANC: Human-free quality estimation of document summaries

O Vasilyev, V Dharnidharka, J Bohannon - arxiv preprint arxiv …, 2020‏ - arxiv.org
We present BLANC, a new approach to the automatic estimation of document summary
quality. Our goal is to measure the functional performance of a summary with an objective …

Multimodal pretraining and generation for recommendation: A tutorial

J Zhu, X Zhou, C Wu, R Zhang, Z Dong - Companion Proceedings of the …, 2024‏ - dl.acm.org
Personalized recommendation stands as a ubiquitous channel for users to explore
information or items aligned with their interests. Nevertheless, prevailing recommendation …

ConvoSumm: Conversation summarization benchmark and improved abstractive summarization with argument mining

AR Fabbri, F Rahman, I Rizvi, B Wang, H Li… - arxiv preprint arxiv …, 2021‏ - arxiv.org
While online conversations can cover a vast amount of information in many different formats,
abstractive text summarization has primarily focused on modeling solely news articles. This …

PENS: A dataset and generic framework for personalized news headline generation

X Ao, X Wang, L Luo, Y Qiao, Q He… - Proceedings of the 59th …, 2021‏ - aclanthology.org
In this paper, we formulate the personalized news headline generation problem whose goal
is to output a user-specific title based on both a user's reading interests and a candidate …

Peek across: Improving multi-document modeling via cross-document question-answering

A Caciularu, ME Peters, J Goldberger, I Dagan… - arxiv preprint arxiv …, 2023‏ - arxiv.org
The integration of multi-document pre-training objectives into language models has resulted
in remarkable improvements in multi-document downstream tasks. In this work, we propose …

“Why is this misleading?”: Detecting News Headline Hallucinations with Explanations

J Shen, J Liu, D Finnie, N Rahmati… - Proceedings of the …, 2023‏ - dl.acm.org
Automatic headline generation enables users to comprehend ongoing news events
promptly and has recently become an important task in web mining and natural language …

Quiz-style question generation for news stories

AD Lelkes, VQ Tran, C Yu - Proceedings of the Web Conference 2021, 2021‏ - dl.acm.org
A large majority of American adults get at least some of their news from the Internet. Even
though many online news products have the goal of informing their users about the news …