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

arXiv: https://arxiv.org/abs/2601.14172 · HTML: https://mlsanity.com/paper/2601.14172/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 76 references that are in the map.
- First posted on arXiv 20 Jan 2026.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Stance Detection on Social Media: State of the Art and Trends](https://mlsanity.com/paper/2006.03644/) (2020)
- [Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey](https://mlsanity.com/paper/1711.04305/) (2017)
- [Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values](https://mlsanity.com/paper/2311.10766/) (2023)
- [The Touch'e23-ValueEval Dataset for Identifying Human Values behind Arguments](https://mlsanity.com/paper/2301.13771/) (2023)
- [MoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social Discussions](https://mlsanity.com/paper/2403.07678/) (2024)
- [ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs](https://mlsanity.com/paper/2409.09586/) (2024)
- [Interpretable Propaganda Detection in News Articles](https://mlsanity.com/paper/2108.12802/) (2021)
- [Do LLMs have Consistent Values?](https://mlsanity.com/paper/2407.12878/) (2024)
- [Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models](https://mlsanity.com/paper/2409.12106/) (2024)
- [Investigating Human Values in Online Communities](https://mlsanity.com/paper/2402.14177/) (2024)
- [MoVa: Towards Generalizable Classification of Human Morals and Values](https://mlsanity.com/paper/2509.24216/) (2025)
- [EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMs](https://mlsanity.com/paper/2505.12792/) (2025)
- [Enhancing Stance Classification on Social Media Using Quantified Moral Foundations](https://mlsanity.com/paper/2310.09848/) (2023)
- [Fine-tuning vs Prompting, Can Language Models Understand Human Values?](https://mlsanity.com/paper/2403.09720/) (2024)
- [The Value of Nothing: Multimodal Extraction of Human Values Expressed by TikTok Influencers](https://mlsanity.com/paper/2501.11770/) (2025)
- [Value Alignment of Social Media Ranking Algorithms](https://mlsanity.com/paper/2509.14434/) (2025)
- [An Empirical Study of Large Language Models for Type and Call Graph Analysis in Python and JavaScript](https://mlsanity.com/paper/2410.00603/) (2024)
- [Beyond Sentiment: Examining the Role of Moral Foundations in User Engagement with News on Twitter](https://mlsanity.com/paper/2502.12009/) (2025)

## Built on by (most cited first, 3 of 3)

- [Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration](https://mlsanity.com/paper/2602.00913/) (2026)
- [More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts](https://mlsanity.com/paper/2605.22641/) (2026)
- [KVpop -- Key-Value Cache Compression with Predictive Online Pruning](https://mlsanity.com/paper/2607.05061/) (2026)

## Abstract (arXiv)

We study neural multi-label classification under severe label imbalance through sentence-level detection of the 19 refined Schwartz human values in 74k English news and manifesto sentences (ValueEval'24 corpus). Each sentence carries a roughly balanced moral-presence label and a 19-way value annotation. First, moral presence is learnable from single sentences: a DeBERTa-base classifier reaches positive-class F1 ≈ 0.73 at the default threshold, which calibration does not improve. Second, comparing direct multi-label detectors with presence-gated hierarchies under an 8 GB consumer-grade GPU budget, we find that gating does not improve over direct prediction, as gate recall becomes a bottleneck. Third, studying lightweight auxiliary signals and small ensembles, we isolate decision-threshold calibration as a decisive, often overlooked factor: a standard text-only baseline already matches the best official ValueEval'24 English run at the default threshold (macro-F1 = 0.282 vs. ≈ 0.28), and tuning the threshold on validation alone raises it to 0.315, most of our overall gain. Lightweight features do not survive a paired per-seed test; a soft-voting ensemble reaches our best macro-F1 = 0.332. Calibration is not architecture-specific: it reproduces on RoBERTa-base, where the gain is larger (+0.043). To our knowledge, this is the first systematic comparison of direct and presence-gated architectures, lightweight feature-augmented encoders, and instruction-tuned Large Language Models (LLMs) at sentence level; benchmarked 7-9B LLMs (zero-/few-shot and QLoRA) lag behind the supervised ensemble under the same budget. We provide empirical guidance for compute-efficient, value-aware NLP models.