---
title: "超越规模与生成：理解基于语言模型的实体匹配"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.24688v1"
permalink: "https://feed.astralor.com/items/itm_307f53e8701825e8f07a99bc"
published: "2026-07-27T17:29:18.000Z"
score: 81
channel: "ai"
tags: ["Qwen3","交叉编码器","双编码器","实体匹配","捷径学习","生成式匹配器"]
---

# 超越规模与生成：理解基于语言模型的实体匹配

## AI 点评

> 这篇论文值得关注，因为它提供了目前最严谨的实体匹配架构比较，特别是揭示了‘大模型未必更好’的反直觉结论，而且开源了所有资源，对从业者非常有参考价值。对于做数据集成、知识图谱构建或使用LLM进行结构化数据处理的团队，这篇论文可以帮助你避开常见的坑。

## 速览

该论文通过控制变量法对三种匹配器架构（双编码器、交叉编码器、生成式匹配器）、三种模型变体和三种模型大小（基于Qwen3系列）进行1215次微调实验，并在9个数据集上评估。研究发现：模型变体对双编码器性能关键；交叉编码器一致优于双编码器，但大模型可缩小差距；生成式匹配器并非普遍优于交叉编码器，仅在与分布偏移或跨数据集迁移时表现更好；大模型更依赖捷径学习，未必性能更好。该研究厘清了架构、模型变体与规模对实体匹配性能的影响。

## 关键点

- 通过1215次微调控制了架构、模型变体和规模的三个因素
- 模型变体对双编码器初始化与表示几何至关重要
- 交叉编码器始终优于双编码器，但大模型可缩小差距
- 生成式匹配器仅在分布偏移和跨数据集时表现优势，且大模型有捷径学习倾向

## 全文

Entity matching identifies records that refer to the same real-world entity. Language models can be adapted to this task through bi-encoder, cross-encoder, and generative matcher architectures. However, prior studies often conflate matcher architecture with differences in model backbone, model variant(reflecting different pretraining objectives), and model size, making it difficult to isolate the sources of performance gains. We address this issue through a controlled factorial study spanning three matcher architectures, three model variants and three model sizes from the Qwen3 family, and nine datasets, totaling 1,215 fine-tuning runs. We also evaluate cross-dataset transferability and computational cost. Our results show that model variant is critical for bi-encoders: embedding-oriented variants provide stronger initialization and more favorable representation geometry predictive of downstream matching performance. Cross-encoders retain a consistent advantage over bi-encoders because they jointly encode record pairs rather than representing each record independently, although larger models partially narrow this gap. Generative matchers do not universally outperform cross-encoders. Instead, their advantages concentrate under distribution shift, including subtle unseen differences in record schemas and cross-dataset transfer. We further find that larger models rely more heavily on shortcut learning and therefore do not necessarily perform better. These findings clarify the factors underlying performance differences across matcher architectures and motivate future research and benchmark designs that better disentangle architectural choices from model-level factors while explicitly evaluating distribution shift and cross-dataset transferability. We release our experimental results, code, training scripts, and evaluation data at https://github.com/Jantory/llm-trained-matcher.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_307f53e8701825e8f07a99bc