The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
arXiv preprint arXiv:2304.10145 , year=
5 Pith papers cite this work, alongside 65 external citations. Polarity classification is still indexing.
5
Pith papers citing it
65
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
An extended annotation scheme with new categories and attributes plus a Gemma-300M-based multi-head classifier achieves 81.6% macro F1 on personal fact classification, outperforming few-shot LLM baselines by nearly 9 points with lower compute.
Real-world jailbreak prompts collected from the wild achieve up to 0.95 attack success rates against major LLMs including GPT-4, with some persisting for over 240 days.
An iterative moderation framework refines and reuses annotation guidelines to improve LLM annotation accuracy on biomedical NER tasks across GPT, Gemini, and DeepSeek models.
Continued pre-training on web data and LLM-ensemble synthetic labels improve multilingual hate speech detection, with gains up to 11% for small models in low-resource settings.
citing papers explorer
-
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
-
An Annotation Scheme and Classifier for Personal Facts in Dialogue
An extended annotation scheme with new categories and attributes plus a Gemma-300M-based multi-head classifier achieves 81.6% macro F1 on personal fact classification, outperforming few-shot LLM baselines by nearly 9 points with lower compute.
-
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Real-world jailbreak prompts collected from the wild achieve up to 0.95 attack success rates against major LLMs including GPT-4, with some persisting for over 240 days.
-
Refining and Reusing Annotation Guidelines for LLM Annotation
An iterative moderation framework refines and reuses annotation guidelines to improve LLM annotation accuracy on biomedical NER tasks across GPT, Gemini, and DeepSeek models.
-
Toward Generalized Cross-Lingual Hateful Language Detection with Web-Scale Data and Ensemble LLM Annotations
Continued pre-training on web data and LLM-ensemble synthetic labels improve multilingual hate speech detection, with gains up to 11% for small models in low-resource settings.