paper-with-me

Papers

CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding

2021-05-23 · Findings (ACL) 2021 8 · Dustin Wright, Isabelle Augenstein

Scientific document understanding is challenging as the data is highly domain specific and diverse. However, datasets for tasks with scientific text require expensive manual annotation and tend to be small and limited to only one or a few fields. At the same time, scientific documents contain many potential training signals, such as citations, which can be used to build large labelled datasets. Given this, we present an in-depth study of cite-worthiness detection in English, where a sentence is labelled for whether or not it cites an external source. To accomplish this, we introduce CiteWorth, a large, contextualized, rigorously cleaned labelled dataset for cite-worthiness detection built from a massive corpus of extracted plain-text scientific documents. We show that CiteWorth is high-quality, challenging, and suitable for studying problems such as domain adaptation. Our best performing cite-worthiness detection model is a paragraph-level contextualized sentence labelling model based on Longformer, exhibiting a 5 F1 point improvement over SciBERT which considers only individual sentences. Finally, we demonstrate that language model fine-tuning with cite-worthiness as a secondary task leads to improved performance on downstream scientific document understanding tasks.

📄 PDF Abstract BibTeX arXiv:2105.10912

Code (1)

copenlu/cite-worth 공식 구현 pytorch

Tasks

document understandingDomain AdaptationLanguage ModelingLanguage ModellingSentence

Methods 이 논문이 사용한 방법론

How do I get a human at Expedia immediately? (2025-2026) How do I get a human at Expedia immediately? (2025 Complete Guide) Most travelers run into a point where self-service isn’t enough, and speaking to a real person becomes the…
Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
AdamW AdamW is a stochastic optimization method that modifies the typical implementation of weight decay in Adam, by decoupling [weight…
WordPiece 설명 없음
How do I complain to Expedia?*ComplainByAgent How do I complain to Expedia? To make a claim on Expedia, call +1(888) (829) (0881) OR +1(805) (330) (4056), or use their Help Center to submit your issue with full booking…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era

2026-02-26 · Kaiwen Shi, Weixiang Sun, Zheyuan Zhang, Lichao Sun 외 arxiv

Scientific research relies on citation integrity, yet large language models (LLMs) have introduced a critical risk: fabricated references that appear plausible but correspond to no real publications. As manual verificati…

Modeling citation worthiness by using attention-based bidirectional long short-term memory networks and interpretable models

2024-05-20 · Tong Zeng, Daniel E. Acuna

Scientist learn early on how to cite scientific sources to support their claims. Sometimes, however, scientists have challenges determining where a citation should be situated -- or, even worse, fail to cite a source alt…

ARCCitation worhtinessCitation worthinessTransfer Learning

CiteCaseLAW: Citation Worthiness Detection in Caselaw for Legal Assistive Writing

2023-05-03 · Mann Khatri, Pritish Wadhwa, Gitansh Satija, Reshma Sheik 외

In legal document writing, one of the key elements is properly citing the case laws and other sources to substantiate claims and arguments. Understanding the legal domain and identifying appropriate citation context or c…

Citation RecommendationCitation worthinessRecommendation SystemsSpecificity

CORE-GPT: Combining Open Access research and large language models for credible, trustworthy question answering

2023-07-06 · David Pride, Matteo Cancellieri, Petr Knoth

In this paper, we present CORE-GPT, a novel question-answering platform that combines GPT-based language models and more than 32 million full-text open access scientific articles from CORE. We first demonstrate that GPT3…

ArticlesQuestion Answering

Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models

2024-02-29 · Chen Qian, Jie Zhang, Wei Yao, Dongrui Liu 외

Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies concentrate on fully pre-trained LLMs to better understand and improve LLMs' trustworthiness. In this paper, to reveal the untapped po…

FairnessMutual Information Estimation