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

Source: [Identifying and Understanding Human Values in Text: A Tailorable LLM-based Architecture](<https://www.sota2.com/research/paper/6a17cbdfdbd7150506f810ed>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-29T05:00:05.519Z

Authors: Eduardo de la Cruz Fern\\'andez, Marcelo Karanik, Sascha Ossowski

Published: 2026-04-07T11:44:58.000Z

## Abstract

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 achieve this, a key aspect is assessing how well these decisions align with human values. To this end, a promising line of research is centred on developing approaches based on Large Language Models (LLMs) to identify human values from text, whether explicit or implicit, enabling their recognition throughout. This paper introduces a LLM-based architecture to detect and quantify the intensity of human values in text, avoiding the limitations of previous approaches tied to specific value theory or complex prompt engineering. The architecture comprises three coordinated modules: one that generates structured value specifications from the foundational texts of any theoretical framework; one that labels texts using these specifications; and one that assigns graded support or resistance based on rhetorical and semantic evidence. This modular approach separates the tasks of conceptualising from detecting human values, creating a scalable and reproducible process driven by value specifications adaptable to various theories. The architecture was instantiated with multiple LLMs and evaluated using the ValueEval dataset. The experiments demonstrate good detection performance, confirming the generality of the pipeline.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-label Value Detection on ValueEval](<https://www.sota2.com/research/sota/multi-label-value-detection-on-valueeval.md>): Multi-label Value Detection; ValueEval; Micro F1: 34.14.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.27373>)

[PDF](<https://arxiv.org/pdf/2605.27373.pdf>)