arXiv cs.AI· Julien Yu, Mihaela Bornea, Avirup Sil, Katrin Kirchhoff·· 12 小时前AI 评分34
图序列化如何影响推理 LLM：知识抽取与结构推理任务研究
Graph Serializations for Reasoning LLMs: A Study Across Knowledge Extraction and Structural Reasoning
AI 导读
研究评估了 15 种图表示格式在 9 种前沿 LLM 配置下对知识抽取与结构图推理任务的影响，发现知识抽取对序列化格式相对不敏感，而结构推理任务的准确率显著受最优格式选择影响。最优表示取决于模型、查询和任务，作者据此提出应将图序列化视为一种动态编排决策。
正文 · 原文
Abstract:The way a knowledge graph is serialized as text for inclusion into LLM context can substantially affect downstream LLM performance, with prior work reporting tens of percentage points variations across formats. However, existing studies consider only a limited set of representations and predate frontier reasoning models, which now offer stronger reasoning, instruction-following, and long-context capabilities. We evaluate 15 graph representation formats across nine frontier LLM configurations on ontology-based knowledge extraction and structural graph reasoning tasks. While knowledge extraction is relatively insensitive to different serialization formats, the choice of the optimal format for structural reasoning tasks significantly affects accuracy. We demonstrate that the optimal representation choice depends on model, query, and task and propose to approach graph serialization as a dynamic orchestration decision.
| Comments: | Accepted to Findings of EMNLP 2026 |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.22734 [cs.AI] |
| (or arXiv:2610.22734v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22734 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Julien Yu [view email]
[v1]
Thu, 15 Oct 2026 23:12:21 UTC (266 KB)
来源：arXiv cs.AI · arxiv.org