Reasoning graphs extracted by an argument-mining pipeline let a GNN attribute LLM-generated essays to the correct model family with more robustness to paraphrasing/backtranslation and better cross-version generalization than a Longformer text baseline.
Title resolution pending
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution
Reasoning graphs extracted by an argument-mining pipeline let a GNN attribute LLM-generated essays to the correct model family with more robustness to paraphrasing/backtranslation and better cross-version generalization than a Longformer text baseline.