Argument-Aware Semantic Alignment of Normative Texts: A Toulmin-Based Neuro-Symbolic Approach

• URL: http://arxiv.org/abs/2608.29529v1
• Date: Sun, 30 Aug 2026 03:30:58 GMT
• Title: Argument-Aware Semantic Alignment of Normative Texts: A Toulmin-Based Neuro-Symbolic Approach
• Abstract summary: This paper asks whether explicit argument structure adds information complementary to neural semantics for aligning requirements.<n>An explicitation step identifies claims, grounds, warrants, qualifiers, and backing and reconstructs enthymemes.<n>On a NERC-CIP to NIST-CSF mapping benchmark, argument-derived features improve alignment over a neuro-symbolic semantic baseline.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semantic alignment between specialized normative texts is challenging when equivalent requirements use different terms, syntax, and levels of abstraction. Lexical overlap, distributional embeddings, and semantic similarity capture topical relatedness but often miss the argumentative structure by which normative claims are supported, qualified, and justified. This paper asks whether explicit argument structure adds information complementary to neural semantics for aligning requirements. We treat cross-standard control mapping as argument-aware semantic alignment and build a neuro-symbolic pipeline that combines neural text representations with Toulmin features. An LLM explicitation step identifies claims, grounds, warrants, qualifiers, and backing and reconstructs enthymemes. These feed an alignment model via argument-aware similarity and structural features. On a NERC-CIP to NIST-CSF mapping benchmark, argument-derived features improve alignment over a neuro-symbolic semantic baseline. Feature selection shows especially strong signal from warrant-related features, indicating that the link between a claim and its supporting reasoning is not captured by conventional similarity alone. A compact claim--grounds--warrant subset remains competitive with the full Toulmin feature set. The results give preliminary evidence that argument structure is a useful intermediate representation for aligning specialized normative texts. Cybersecurity standards are used as a controlled testbed, not as proof of domain-independent generalization. The argument graphs produced by LLM explicitation may also support later work on retrieval, reasoning, and explanation over normative text.

Related papers

• Does Syntax Matter? A Graph-Augmented Variational Topic Model for Computational Social Sciences [51.56484100374058]
  This paper introduces the Structural Contextual Probabilistic Topic Model ( SCPTM), an architecture that incorporates syntactic dependency relations into topic inference.<n>We evaluate seven topic modeling techniques across four corpora differing in register and discourse structure.<n>Results show that SCPTM's neural architecture yields substantial gains in document-topic alignment over generative baselines.
  arXiv  Detail & Related papers  (2026-09-07T17:39:06Z)
• Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach [58.15427952222424]
  General-purpose text embeddings are widely deployed for such tasks, but broad semantic similarity can place semantically similar yet task-distinct examples.<n>We introduce Prototype-Guided Contrastive Learning (PGCL), a prototype-guided geometric regularization module built on top of frozen text embeddings.
  arXiv  Detail & Related papers  (2026-08-15T13:19:25Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge [50.009682083079205]
  We investigate whether contextual recall emerges from pretraining alone.<n>We show that finetuning on tasks requiring implicit inference, distinct from the ICL evaluation, triggers the emergence of contextual recall.<n>For mechanistic insight, we derive a construction for an attention-only transformer that replicates the transition from factual to contextual recall.
  arXiv  Detail & Related papers  (2026-03-21T22:46:55Z)
• The Algebra of Meaning: Why Machines Need Montague More Than Moore's Law [0.32904041852873017]
  We argue that moderation, brittle, and opaque semantics are symptoms of missing type-theoretic semantics rather than data or scale limitations.<n>Building on Montague's view of language as typed, compositional algebra, we recast alignment as a parsing problem.<n>We present Savai, a neuro-symbol-language that compiles utterances into descriptive-style logical forms.
  arXiv  Detail & Related papers  (2025-10-08T01:22:26Z)
• StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching [10.000850856259866]
  StructCoh is a graph-enhanced contrastive learning framework.<n>A hierarchical contrastive objective enforces consistency at multiple granularities.<n>Experiments on three legal document matching benchmarks and academic plagiarism detection datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2025-09-02T07:21:36Z)
• AKReF: An argumentative knowledge representation framework for structured argumentation [0.9626666671366837]
  We present a framework to convert argumentative texts into argument knowledge graphs (AKG)<n>The proposed argumentative knowledge representation framework (AKReF) extends the theoretical foundation.<n>We show its application in complex analyses such as extracting a conflict-free set and a maximal set of admissible arguments.
  arXiv  Detail & Related papers  (2025-05-31T21:11:30Z)
• Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures [104.32063681736349]
  We present an approach to describe predicate-argument structures using natural language definitions instead of discrete labels. Our experiments and analyses on PropBank-style and FrameNet-style, dependency-based and span-based SRL also demonstrate that a flexible model with an interpretable output does not necessarily come at the expense of performance.
  arXiv  Detail & Related papers  (2022-12-02T11:19:16Z)
• Contextualized Semantic Distance between Highly Overlapped Texts [85.1541170468617]
  Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence as neighboring words and use masked language modeling (MLM) to predict the distributions on their positions. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts.
  arXiv  Detail & Related papers  (2021-10-04T03:59:15Z)
• Refining Implicit Argument Annotation for UCCA [6.873471412788333]
  This paper proposes a typology for fine-grained implicit argument annotation on top of Universal Cognitive Conceptual's foundational layer. The proposed implicit argument categorisation is driven by theories of implicit role interpretation and consists of six types: Deictic, Generic, Genre-based, Type-identifiable, Non-specific, and Iterated-set.
  arXiv  Detail & Related papers  (2020-05-26T17:24:15Z)

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.