mlsanityData to 7 Oct 2026

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

arXiv 2602.00913 ↗First posted 31 Jan 2026cs.CL cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (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 compute-frugal budget. Rather than proposing a new architecture, we compare direct supervised transformers, hard HOrightarrowvalues pipelines, PresencerightarrowHOrightarrowvalues cascades, compact instruction-tuned large language models (LLMs), QLoRA, and low-cost upgrades such as threshold tuning and small ensembles. HO categories are learnable: the easiest bipolar pair, Growth vs. Self-Protection, reaches Macro-F1=0.58. The most reliable gains come from calibration and ensembling: threshold tuning improves Social Focus vs. Personal Focus from 0.41 to 0.57 (+0.16), transformer soft voting lifts Growth from 0.286 to 0.303, and a Transformer+LLM hybrid reaches 0.353 on Self-Protection. In contrast, hard hierarchical gating does not consistently improve the end task. Compact LLMs also underperform supervised encoders as stand-alone systems, although they sometimes add useful diversity in hybrid ensembles. Under this benchmark, the HO structure is more useful as an inductive bias than as a rigid routing rule.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 81 references that are in the map. First posted on arXiv 31 Jan 2026.

Builds on

27 of 81 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  8. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  9. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
  10. 2013Crowdsourcing a Word-Emotion Association Lexiconcited by 193
  11. 2023Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Valuescited by 49
  12. 2019MoralStrength: Exploiting a Moral Lexicon and Embedding Similarity for Moral Foundations Predictioncited by 31
15 more
  1. 2023The Touch'e23-ValueEval Dataset for Identifying Human Values behind Argumentscited by 27
  2. 2024ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMscited by 20
  3. 2018An Analysis of Hierarchical Text Classification Using Word Embeddingscited by 16
  4. 2022Hierarchical classification at multiple operating pointscited by 14
  5. 2024Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approachescited by 13
  6. 2024Do LLMs have Consistent Values?cited by 13
  7. 2024Measuring Human and AI Values Based on Generative Psychometrics with Large Language Modelscited by 13
  8. 2024Investigating Human Values in Online Communitiescited by 10
  9. 2024WorryWords: Norms of Anxiety Association for over 44k English Wordscited by 10
  10. 2025MoVa: Towards Generalizable Classification of Human Morals and Valuescited by 7
  11. 2024Fine-tuning vs Prompting, Can Language Models Understand Human Values?cited by 4
  12. 2025The Value of Nothing: Multimodal Extraction of Human Values Expressed by TikTok Influencerscited by 4
  13. 2025EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMscited by 4
  14. 2025Cultural Value Alignment in Large Language Models: A Prompt-based Analysis of Schwartz Values in Gemini, ChatGPT, and DeepSeekcited by 4
  15. 2026Human Values in a Single Sentence: Moral Presence, Hierarchies, and Transformer Ensembles on the Schwartz Continuumcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Textscited by 1
  2. 2026KVpop -- Key-Value Cache Compression with Predictive Online Pruningcited by 1
  3. 2026From Trial by Fire To Sleep Like a Baby: A Lexicon of Anxiety Associations for 20k English Multiword Expressionscited by 0