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

• URL: http://arxiv.org/abs/2601.14007v1
• Date: Tue, 20 Jan 2026 14:26:58 GMT
• Title: BACH-V: Bridging Abstract and Concrete Human-Values in Large Language Models
• Abstract summary: We introduce an abstraction-grounding framework that decomposes conceptual understanding into three capacities.<n>Using human values as a testbed, we employ probing (detecting value traces in internal activations) and steering (modifying representations to shift behavior)<n>We find that diagnostic probes trained solely on abstract value descriptions reliably detect the same values in concrete event narratives and decision reasoning.
• Score: 13.750822025397904
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• Enhancing Structural Mapping with LLM-derived Abstractions for Analogical Reasoning in Narratives [13.352345916789337]
  Analogical reasoning is a key driver of human generalization in problem-solving and argumentation.<n>We propose a modular framework named YARN, which uses LLMs to decompose narratives into units, abstract these units, and then passes them to a mapping component that aligns elements across stories to perform analogical reasoning.<n>Our experiments reveal that abstractions consistently improve model performance, resulting in competitive or better performance than end-to-end LLM baselines.
  arXiv  Detail & Related papers  (2026-03-31T16:57:11Z)
• Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models [28.102903742881576]
  We introduce a framework for abstraction-guided reasoning that explicitly separates structural inference from lexical semantics.<n>We show that abstraction-aligned steering reduces content-driven errors and improves validity-sensitive performance.
  arXiv  Detail & Related papers  (2026-02-02T18:48:44Z)
• Using Large Language Models for Abstraction of Planning Domains - Extended Version [6.021787236982658]
  We model the agent's concrete behaviors in PDDL and investigate the use of in-context learning with large language models (LLMs)<n>We consider three categories of abstractions: abstraction of choice of alternative concrete actions, abstraction of sequences of concrete actions, and abstraction of action/predicate parameters.<n>The generated abstract PDDL domains and problem instances are then checked by symbolic validation tools as well as human experts.
  arXiv  Detail & Related papers  (2025-10-23T06:27:03Z)
• ActivationReasoning: Logical Reasoning in Latent Activation Spaces [43.17973499652433]
  Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control.<n>We introduce ActivationReasoning (AR), a framework that embeds explicit logical reasoning into the latent space of LLMs.<n>AR scales robustly with reasoning complexity, generalizes to abstract and context-sensitive tasks, and transfers across model backbones.
  arXiv  Detail & Related papers  (2025-10-21T00:21:04Z)
• Causal Abstraction Inference under Lossy Representations [53.18851962820361]
  We introduce a new type of abstractions called projected abstractions that generalize existing definitions to accommodate lossy representations.<n>We show how to construct a projected abstraction from the low-level model and how it translates equivalent observational, interventional, and counterfactual causal queries from low to high-level.
  arXiv  Detail & Related papers  (2025-09-25T21:20:42Z)
• Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective [59.7140089198992]
  We develop a mathematic framework that defines abstract reasoning as the ability to extract essential patterns.<n>We introduce two novel complementary metrics: (scoreGamma) measures basic reasoning accuracy, while (scoreDelta) quantifies a model's reliance on specific symbols.
  arXiv  Detail & Related papers  (2025-05-28T09:02:45Z)
• Seeing the Abstract: Translating the Abstract Language for Vision Language Models [13.065703240655973]
  We focus our investigation on the fashion domain, a highly-representative field with abstract expressions.<n>By analyzing recent large-scale multimodal fashion datasets, we find that abstract terms have a dominant presence.<n>We propose a training-free and model-agnostic method, Abstract-to-Concrete Translator (ACT), to shift abstract representations towards well-represented concrete ones.
  arXiv  Detail & Related papers  (2025-05-06T07:14:10Z)
• Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions [25.337811496479265]
  Chain-of-Though (CoT) represents a common strategy for reasoning in Large Language Models.<n>We present QuaSAR, a variation of CoT that guides LLMs to operate at a higher level of abstraction via quasi-symbolic explanations.<n>Our experiments show that quasi-symbolic abstractions can improve CoT-based methods by up to 8% accuracy.
  arXiv  Detail & Related papers  (2025-02-18T07:58:48Z)
• Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning [63.58935783293342]
  Causal Bisimulation Modeling (CBM) is a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. CBM's learned implicit dynamics models identify the underlying causal relationships and state abstractions more accurately than explicit ones.
  arXiv  Detail & Related papers  (2024-01-23T05:43:15Z)
• AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph [62.685920585838616]
  abstraction ability is essential in human intelligence, which remains under-explored in language models. We present AbsPyramid, a unified entailment graph of 221K textual descriptions of abstraction knowledge.
  arXiv  Detail & Related papers  (2023-11-15T18:11:23Z)
• Does Deep Learning Learn to Abstract? A Systematic Probing Framework [69.2366890742283]
  Abstraction is a desirable capability for deep learning models, which means to induce abstract concepts from concrete instances and flexibly apply them beyond the learning context. We introduce a systematic probing framework to explore the abstraction capability of deep learning models from a transferability perspective.
  arXiv  Detail & Related papers  (2023-02-23T12:50:02Z)
• Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization [49.00409552570441]
  We study the role of conceptualization in commonsense reasoning, and formulate a framework to replicate human conceptual induction. We apply the framework to ATOMIC, a large-scale human-annotated CKG, aided by the taxonomy Probase.
  arXiv  Detail & Related papers  (2022-06-03T12:24:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.