通过因果干预解析多语言检索模型的匹配机制
Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal Interventions
- 用激活修补法分离模型中关键词与文档长度的贡献
- 跨语言验证词频信息在后期层集中于CLS token
- 为检索模型可解释性研究提供可复现的方法框架
本可复现研究分析并扩展了《用于逆向工程神经检索模型相关性计算的公理化因果干预》一文，探究神经检索模型如何编码词频等任务相关属性。我们复现了原论文的关键实验，确认查询词信息确实被模型编码。研究进一步将激活修补法应用于西班牙语和中文数据集，并检验文档长度信息是否也被编码。结果表明，所设计的激活修补方法能有效隔离模型特定组件和标记的行为。此外，词频位置的信息在不同语言间具有泛化性，且在深层网络中，序列级任务信息表现为CLS token中的表示。研究强调了信息检索领域可解释性及机器学习研究可复现性的必要性。代码已公开于 https://github.com/OliverSavolainen/axiomatic-ir-reproduce。
原文摘要 · Abstract (English)
This reproducibility study analyzes and extends the paper "Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models," which investigates how neural retrieval models encode task-relevant properties such as term frequency. We reproduce key experiments from the original paper, confirming that information on query terms is captured in the model encoding. We extend this work by applying activation patching to Spanish and Chinese datasets and by exploring whether document-length information is encoded in the model as well. Our results confirm that the designed activation patching method can isolate the behavior to specific components and tokens in neural retrieval models. Moreover, our findings indicate that the location of term frequency generalizes across languages and that in later layers, the information for sequence-level tasks is represented in the CLS token. The results highlight the need for further research into interpretability in information retrieval and reproducibility in machine learning research. Our code is available at https://github.com/OliverSavolainen/axiomatic-ir-reproduce.
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。