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

arXiv:2605.22641 · cs.CL, cs.AI, cs.LG · Submitted 2026-05-21 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-05-21

Updated: 2026-09-07

Comments: Accepted to Findings of the Association for Computational Linguistics: EMNLP 2026. Code: https://github.com/VictorMYeste/human-value-detection-context-rag, best model: https://huggingface.co/VictorYeste/value-context-rag-deberta-v3-base-doc-rag, 18 pages, 3 figures

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

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

The gist: Detecting Schwartz values in political texts is hard: cues are often implicit, and neighboring values differ by fine distinctions.

Terminology

Abstract

Detecting Schwartz values in political texts is hard: cues are often implicit, and neighboring values differ by fine distinctions. Two remedies are widely assumed to help: more surrounding document text, and explicit moral knowledge. Knowledge-based retrieval has improved benchmarks elsewhere, but whether either transfers here is untested, because published systems vary context, knowledge, and model family at once. We separate these factors under matched conditions on the ValuesML/Touché ValueEval format. The input ranges from the target sentence to a local window to the full document. Retrieval is either absent or drawn from a curated moral knowledge base, injected by early, late, or cross-attention fusion. Supervised DeBERTa-v3 encoders are compared against zero-shot LLMs from 12B to 123B. More context is not uniformly better: full-document input improves the encoders by 2.5-3.8 macro-F1 points but does not consistently help the LLMs. Retrieved knowledge helps more reliably, improving every model family and context under early fusion. A control substituting random knowledge-base entries shows the families gain differently: LLMs from relevance, encoders from exposure to the value ontology. Neither larger encoders nor larger LLMs guarantee gains, and early fusion outperforms both trainable variants. Value-sensitive NLP should evaluate context, knowledge, and model family jointly.

Sources

Related papers