用知识图谱增强小模型推理，提升复杂逻辑任务表现。
Enhancing Small Language Models Reasoning through Knowledge Graph Grounding
- 将小模型变成智能代理，调用抽取事实和专家推理工具
- 知识图谱提示使性能提升1.5到2倍，但依赖准确的事实提取
- 适合研究低资源智能体与神经符号系统融合的学者
尽管大语言模型在零样本推理上达到新高度，但其部署成本高且环境负担重。小语言模型（SLMs）是可持续替代方案，但在需要复杂多跳逻辑推理的任务中易出错。本文提出一种神经符号代理框架，针对Gemma 3（1B、4B）和Llama 3.2（3B）在CLUTRR亲属关系基准上的表现进行改进。方法将SLM转化为最小化代理，通过两个专用工具调用：extract_facts用于符号三元组提取，get_hint通过关系图卷积网络（RGCN）获取专家推理提示。在两种配置下评估：一种使用真实三元组（Oracle场景），另一种依赖自提取知识（现实场景）。结果表明，基于RGCN的提示使性能比仅依赖故事的基线提升1.5至2倍，但受限于提取瓶颈和序列推导脆弱性，早期错误会沿多跳链累积。此外，特定架构中存在“干扰效应”，即使有专家提示，噪声自生成事实仍会降低性能。本工作揭示了低资源代理系统中符号接地的挑战，并为神经符号代理流程中的迭代验证提供路线图。
原文摘要 · Abstract (English)
Although large language models (LLMs) have set benchmarks for zero-shot reasoning, their deployment remains cost-prohibitive and environmentally taxing. Small Language Models (SLMs) offer a sustainable alternative, but prone to errors, on tasks requiring complex, multi-hop logical grounding. We investigate a neuro-symbolic agentic framework to enhance the reasoning capabilities of SLMs, specifically Gemma 3 (1B, 4B) and Llama 3.2 (3B), using the CLUTRR kinship benchmark. Our approach transforms the SLM into a minimalist agent utilizing two specialized tool calls: extract_facts for symbolic triplet extraction and get_hint for expert reasoning via a Relational Graph Convolutional Network (RGCN). We evaluate these models across two configurations, both in an Oracle scenario with ground-truth triplets and a Realistic scenario relying on self-extracted knowledge. Our results reveal that while RGCN-derived hints provide a 1.5 - 2x performance gain over story-only baselines, the system is constrained by the extraction bottleneck and sequential deductive fragility, where early extraction errors compound over multi-hop chains. Furthermore, we identify a "distraction effect" in specific architectures where noisy, self-generated facts degrade performance despite the presence of expert hints. This work characterizes the challenges of symbolic grounding in low-resource agentic systems and provides a roadmap for iterative verification in neuro-symbolic agentic pipelines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。