paper-with-me

홈 › Papers

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing

2025-09-24 · Xinnan Dai, Chung-Hsiang Lo, Kai Guo, Shenglai Zeng, Dongsheng Luo, Jiliang Tang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.20336

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

2025-07-11 · Xinnan Dai, Kai Yang, Jay Revolinsky, Kai Guo 외 arxiv

Recent studies suggest that large language models (LLMs) possess the capability to solve graph reasoning tasks. Notably, even when graph structures are embedded within textual descriptions, LLMs can still effectively ans…

Spectral Journey: How Transformers Predict the Shortest Path

2025-02-12 · Andrew Cohen, Andrey Gromov, Kaiyu Yang, Yuandong Tian

Decoder-only transformers lead to a step-change in capability of large language models. However, opinions are mixed as to whether they are really planning or reasoning. A path to making progress in this direction is to s…

DecoderGraph Embedding

The Expressive Power of Transformers with Chain of Thought

2023-10-11 · William Merrill, Ashish Sabharwal

Recent theoretical work has identified surprisingly simple reasoning problems, such as checking if two nodes in a graph are connected or simulating finite-state machines, that are provably unsolvable by standard transfor…

Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers

2024-11-18 · Tiberiu Musat

In this paper, I introduce the retrieval problem, a simple yet common reasoning task that can be solved only by transformers with a minimum number of layers, which grows logarithmically with the input size. I empirically…

Retrieval

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers

2023-10-05 · Anna Langedijk, Hosein Mohebbi, Gabriele Sarti, Willem Zuidema 외

In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformer…

DecoderLogical ReasoningMachine TranslationQuestion Answering+2