홈 › Papers

The Touché23-ValueEval Dataset for Identifying Human Values behind Arguments

2023-01-31 · Nailia Mirzakhmedova, Johannes Kiesel, Milad Alshomary, Maximilian Heinrich, Nicolas Handke, Xiaoni Cai, Barriere Valentin, Doratossadat Dastgheib, Omid Ghahroodi, Mohammad Ali Sadraei, Ehsaneddin Asgari, Lea Kawaletz, Henning Wachsmuth, Benno Stein

We present the Touch\'e23-ValueEval Dataset for Identifying Human Values behind Arguments. To investigate approaches for the automated detection of human values behind arguments, we collected 9324 arguments from 6 diverse sources, covering religious texts, political discussions, free-text arguments, newspaper editorials, and online democracy platforms. Each argument was annotated by 3 crowdworkers for 54 values. The Touch\'e23-ValueEval dataset extends the Webis-ArgValues-22. In comparison to the previous dataset, the effectiveness of a 1-Baseline decreases, but that of an out-of-the-box BERT model increases. Therefore, though the classification difficulty increased as per the label distribution, the larger dataset allows for training better models.

📄 PDF Abstract BibTeX arXiv:2301.13771

Code (1)

https://zenodo.org/record/7550385 공식 구현

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Adam 설명 없음

Weight Decay 설명 없음

Multi-Head Attention 설명 없음

Residual Connection 설명 없음

Epicurus at SemEval-2023 Task 4: Improving Prediction of Human Values behind Arguments by Leveraging Their Definitions

2023-02-27 · Christian Fang, Qixiang Fang, Dong Nguyen

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 …

Survey

Identifying and Understanding Human Values in Text: A Tailorable LLM-based Architecture

2026-04-07 · Eduardo de la Cruz Fernández, Marcelo Karanik, Sascha Ossowski arxiv

As intelligent systems become more autonomous, the scientific community focuses on creating decision-making mechanisms that include ethical and moral considerations, unlike traditional utility-maximisation models. To ach…

Prompt Engineering

More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts

2026-05-21 · Víctor Yeste, Paolo Rosso arxiv

Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions between neighboring values. We study when context and explicit moral know…

Human Values in a Single Sentence: Moral Presence, Hierarchies, and Transformer Ensembles on the Schwartz Continuum

2026-01-20 · Víctor Yeste, Paolo Rosso arxiv

We study sentence-level detection of the 19 human values in the refined Schwartz continuum in about 74k English sentences from news and political manifestos (ValueEval'24 corpus). Each sentence is annotated with value pr…

Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration

2026-01-31 · Víctor Yeste, Paolo Rosso arxiv

Human value detection from single sentences is a sparse, imbalanced multi-label task. We study whether Schwartz higher-order (HO) categories help this setting on ValueEval'24 / ValuesML (74K English sentences) under a co…