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

arXiv:2601.14172 · cs.CL, cs.AI · Submitted 2026-01-20 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-01-20

Updated: 2026-09-14

Comments: Code: https://github.com/VictorMYeste/human-value-detection, models: https://huggingface.co/papers/2601.14172. 68 pages, 4 figures, 10 tables; supplementary material in the ancillary files

Code: https://github.com/VictorMYeste/human-value-detection

License: http://creativecommons.org/licenses/by/4.0/

The gist: 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

Terminology

Abstract

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 F 1 about 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- F 1 = 0.282 vs. about 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- F 1 = 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.

Sources

Related papers