Imagen de Portada

Navigating Prompt Complexity for Zero-Shot Classification: A Study of Large Language Models in Computational Social Science

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mu, Yida, Wu, Ben P., Thorne, William, Robinson, Ambrose, Aletras, Nikolaos, Scarton, Carolina, Bontcheva, Kalina, Song, Xingyi
Formato:	Preprint
Publicado:	2023
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Examining the Limitations of Computational Rumor Detection Models Trained on Static Datasets
por: Mu, Yida, et al.
Publicado: (2023)

Enhancing Data Quality through Simple De-duplication: Navigating Responsible Computational Social Science Research
por: Mu, Yida, et al.
Publicado: (2024)

GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification
por: Singh, Iknoor, et al.
Publicado: (2025)

Large Language Models Offer an Alternative to the Traditional Approach of Topic Modelling
por: Mu, Yida, et al.
Publicado: (2024)

Addressing Topic Granularity and Hallucination in Large Language Models for Topic Modelling
por: Mu, Yida, et al.
Publicado: (2024)

Breaking Language Barriers with MMTweets: Advancing Cross-Lingual Debunked Narrative Retrieval for Fact-Checking
por: Singh, Iknoor, et al.
Publicado: (2023)

Examining Temporalities on Stance Detection towards COVID-19 Vaccination
por: Mu, Yida, et al.
Publicado: (2023)

A Lightweight Approach for User and Keyword Classification in Controversial Topics
por: Zareie, Ahmad, et al.
Publicado: (2025)

A Dataset for Analysing News Framing in Chinese Media
por: Cook, Owen, et al.
Publicado: (2025)

The False COVID-19 Narratives That Keep Being Debunked: A Spatiotemporal Analysis
por: Singh, Iknoor, et al.
Publicado: (2021)

Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals
por: Leite, João A., et al.
Publicado: (2023)

Weakly supervised veracity classification with LLM-predicted credibility signals
por: Leite, João Augusto, et al.
Publicado: (2025)

A Cross-Domain Study of the Use of Persuasion Techniques in Online Disinformation
por: Leite, João A., et al.
Publicado: (2024)

LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
por: Leite, João A., et al.
Publicado: (2026)

EUvsDisinfo: A Dataset for Multilingual Detection of Pro-Kremlin Disinformation in News Articles
por: Leite, João A., et al.
Publicado: (2024)

Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification
por: Razuvayevskaya, Olesya, et al.
Publicado: (2023)

UKElectionNarratives: A Dataset of Misleading Narratives Surrounding Recent UK General Elections
por: Haouari, Fatima, et al.
Publicado: (2025)

Truth with a Twist: The Rhetoric of Persuasion in Professional vs. Community-Authored Fact-Checks
por: Razuvayevskaya, Olesya, et al.
Publicado: (2026)

A Multilingual, Large-Scale Study of the Interplay between LLM Safeguards, Personalisation, and Disinformation
por: Leite, João A., et al.
Publicado: (2025)

Label Set Optimization via Activation Distribution Kurtosis for Zero-shot Classification with Generative Models
por: Li, Yue, et al.
Publicado: (2024)

Improving Multimodal Classification of Social Media Posts by Leveraging Image-Text Auxiliary Tasks
por: Villegas, Danae Sánchez, et al.
Publicado: (2023)

Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond
por: Goldsack, Tomas, et al.
Publicado: (2025)

Can We Identify Stance Without Target Arguments? A Study for Rumour Stance Classification
por: Li, Yue, et al.
Publicado: (2023)

Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims
por: Heppell, Freddy, et al.
Publicado: (2024)

Incorporating Attribution Importance for Improving Faithfulness Metrics
por: Zhao, Zhixue, et al.
Publicado: (2023)

Vocabulary-level Memory Efficiency for Language Model Fine-tuning
por: Williams, Miles, et al.
Publicado: (2023)

Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models
por: Zhao, Zhixue, et al.
Publicado: (2024)

On the Impact of Calibration Data in Post-training Quantization and Pruning
por: Williams, Miles, et al.
Publicado: (2023)

SCRum-9: Multilingual Stance Classification over Rumours on Social Media
por: Li, Yue, et al.
Publicado: (2025)

We Need to Talk About Classification Evaluation Metrics in NLP
por: Vickers, Peter, et al.
Publicado: (2024)

Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference
por: Thorne, William, et al.
Publicado: (2024)

Hostility Detection in UK Politics: A Dataset on Online Abuse Targeting MPs
por: Pandya, Mugdha, et al.
Publicado: (2024)

Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization
por: Chrysostomou, George, et al.
Publicado: (2023)

Navigating the Prompt Space: Improving LLM Classification of Social Science Texts Through Prompt Engineering
por: Gunes, Erkan, et al.
Publicado: (2026)

Self-calibration for Language Model Quantization and Pruning
por: Williams, Miles, et al.
Publicado: (2024)

Where does output diversity collapse in post-training?
por: Karouzos, Constantinos, et al.
Publicado: (2026)

An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift
por: Karouzos, Constantinos, et al.
Publicado: (2026)

How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?
por: Yamaguchi, Atsuki, et al.
Publicado: (2024)

An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference
por: Yamaguchi, Atsuki, et al.
Publicado: (2024)

Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks
por: Yamaguchi, Atsuki, et al.
Publicado: (2026)