BACH-V: Bridging Abstract and Concrete Human-Values in Large Language Models

TL;DR

This paper investigates how large language models understand and utilize human values by analyzing their internal representations, demonstrating that they maintain structured, transferable value concepts bridging abstract understanding and concrete decision-making.

Contribution

The paper introduces an abstraction-grounding framework and empirical methods to analyze how LLMs represent and manipulate human values across different levels of abstraction.

Findings

Probes detect consistent value traces across abstract and concrete contexts.

Interventions on value representations causally influence concrete decisions.

Abstract value interpretations remain stable despite manipulations.

Abstract

Do large language models (LLMs) genuinely understand abstract concepts, or merely manipulate them as statistical patterns? We introduce an abstraction-grounding framework that decomposes conceptual understanding into three capacities: interpretation of abstract concepts (Abstract-Abstract, A-A), grounding of abstractions in concrete events (Abstract-Concrete, A-C), and application of abstract principles to regulate concrete decisions (Concrete-Concrete, C-C). Using human values as a testbed - given their semantic richness and centrality to alignment - we employ probing (detecting value traces in internal activations) and steering (modifying representations to shift behavior). Across six open-source LLMs and ten value dimensions, probing shows that diagnostic probes trained solely on abstract value descriptions reliably detect the same values in concrete event narratives and decision reasoning, demonstrating cross-level transfer. Steering reveals an asymmetry: intervening on value representations causally shifts concrete judgments and decisions (A-C, C-C), yet leaves abstract interpretations unchanged (A-A), suggesting that encoded abstract values function as stable anchors rather than malleable activations. These findings indicate LLMs maintain structured value representations that bridge abstraction and action, providing a mechanistic and operational foundation for building value-driven autonomous AI systems with more transparent, generalizable alignment and control.