Read original ↗
paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago

Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution

Given the current trend to employ large language models (LLMs) in almost any imaginable context, LLM-generated text detection and authorship attribution have become a pressing issue. Prior work has primarily focused on surface-level linguistic features, an approach shown to be susceptible to paraphrasing and other obfuscation techniques. In this paper, we go beyond the linguistic surface, extracting and analysing reasoning structures in LLM-generated texts with the goal of capturing more complex signals of LLM authorship. We propose a graph neural network approach that leverages reasoning grap

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

  • FuzzySimilar title/name (fuzzy) · 59%rasbt/reasoning-from-scratch

    Fuzzy title match (0.73): “Show Me How You Reason and I'll Tell You Who You Are: Reason” ≈ “rasbt/reasoning-from-scratch”

  • LinkedLinked via arxiv author · 85%Zlata Kikteva

    Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution

  • LinkedLinked via arxiv author · 85%Artur Romazanov

    Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution

  • LinkedLinked via arxiv author · 85%Annette Hautli-Janisz

    Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution

  • LinkedLinked via arxiv author · 85%Ramon Ruiz-Dolz

    Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution

Implements (incoming)

authored (incoming)

Related across the graph

Topics