Epicurus at SemEval-2023 Task 4: Improving Prediction of Human Values behind Arguments by Leveraging Their Definitions
Not on the map. Why?
Abstract (arXiv)
We describe our experiments for SemEval-2023 Task 4 on the identification of human values behind arguments (ValueEval). Because human values are subjective concepts which require precise definitions, we hypothesize that incorporating the definitions of human values (in the form of annotation instructions and validated survey items) during model training can yield better prediction performance. We explore this idea and show that our proposed models perform better than the challenge organizers' baselines, with improvements in macro F1 scores of up to 18%.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 9 of its 40 references that are in the map. First posted on arXiv 27 Feb 2023.
Builds on
9 of 40 references.
References · 9
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
- 2019Macro F1 and Macro F1cited by 70
- 2020Learning to Recognize Dialect Featurescited by 29
- 2023The Touch'e23-ValueEval Dataset for Identifying Human Values behind Argumentscited by 27
- 2022Evaluating the Construct Validity of Text Embeddings with Application to Survey Questionscited by 7
- 2022Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Userscited by 5
- 2022Improving Stance Detection by Leveraging Measurement Knowledge from Social Sciences: A Case Study of Dutch Political Tweets and Traditional Gender Role Divisioncited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 2.
4 papers.
- 2024A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practicecited by 26
- 2025Value Lens: Using Large Language Models to Understand Human Valuescited by 3
- 2026More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Textscited by 1
- 2026Identifying and Understanding Human Values in Text: A Tailorable LLM-based Architecturecited by 0
- 2026More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts21 May 2026
- 2026Identifying and Understanding Human Values in Text: A Tailorable LLM-based Architecture7 Apr 2026
- 2025Value Lens: Using Large Language Models to Understand Human Values4 Dec 2025
- 2024A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice25 Apr 2024