Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dai, Xinnan, Lo, Chung-Hsiang, Guo, Kai, Zeng, Shenglai, Luo, Dongsheng, Tang, Jiliang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912603028062208
author Dai, Xinnan
Lo, Chung-Hsiang
Guo, Kai
Zeng, Shenglai
Luo, Dongsheng
Tang, Jiliang
author_facet Dai, Xinnan
Lo, Chung-Hsiang
Guo, Kai
Zeng, Shenglai
Luo, Dongsheng
Tang, Jiliang
contents Transformer-based LLMs demonstrate strong performance on graph reasoning tasks, yet their internal mechanisms remain underexplored. To uncover these reasoning process mechanisms in a fundamental and unified view, we set the basic decoder-only transformers and explain them using the circuit-tracer framework. Through this lens, we visualize reasoning traces and identify two core mechanisms in graph reasoning: token merging and structural memorization, which underlie both path reasoning and substructure extraction tasks. We further quantify these behaviors and analyze how they are influenced by graph density and model size. Our study provides a unified interpretability framework for understanding structural reasoning in decoder-only Transformers.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20336
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
Dai, Xinnan
Lo, Chung-Hsiang
Guo, Kai
Zeng, Shenglai
Luo, Dongsheng
Tang, Jiliang
Machine Learning
Artificial Intelligence
Transformer-based LLMs demonstrate strong performance on graph reasoning tasks, yet their internal mechanisms remain underexplored. To uncover these reasoning process mechanisms in a fundamental and unified view, we set the basic decoder-only transformers and explain them using the circuit-tracer framework. Through this lens, we visualize reasoning traces and identify two core mechanisms in graph reasoning: token merging and structural memorization, which underlie both path reasoning and substructure extraction tasks. We further quantify these behaviors and analyze how they are influenced by graph density and model size. Our study provides a unified interpretability framework for understanding structural reasoning in decoder-only Transformers.
title Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.20336