arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.14869cs.AIstat.ML
收藏

概念影响:利用可解释性以提高训练数据归因的性能和效率

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution

EleutherAI;University of Toronto(多伦多大学)

Matthew Kowal, Goncalo Paulo, Louis Jaburi, Tom Tseng, Lev E McKinney, Stefan Heimersheim, Aaron David Tucker, Adam Gleave, Kellin Pelrine

AI总结:

本文提出概念影响方法,通过利用模型中的可解释结构,提高训练数据归因的性能和效率,实现更可扩展和可控的模型行为。

摘要:

随着大语言模型被越来越多地训练和微调,从业者需要方法来识别哪些训练数据驱动特定行为,尤其是非预期的行为。训练数据归因(TDA)方法通过估计数据点影响来解决这个问题。现有方法如影响函数在计算上耗费巨大且基于单个测试示例,这可能导致结果偏向于语法而非语义相似性。为了解决这些可扩展性和影响抽象行为的问题,我们利用模型中的可解释结构进行归因。首先,我们引入了概念影响,将模型行为归因于语义方向(如线性探针或稀疏自编码器特征),而不是个别测试示例。其次,我们展示简单的基于探针的归因方法是概念影响的一阶近似,其性能可比而速度快一个数量级。我们通过新兴的对齐基准和真实的后训练数据集经验验证了概念影响和近似方法,并证明它们在性能上与经典影响函数相当,但可扩展性显著更高。更广泛地说,我们展示了在传统TDA流程中整合可解释结构可以实现更可扩展、可解释和更可控的模型行为通过数据。

英文摘要:

As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by estimating datapoint influence. Existing approaches like influence functions are both computationally expensive and attribute based on single test examples, which can bias results toward syntactic rather than semantic similarity. To address these issues of scalability and influence to abstract behavior, we leverage interpretable structures within the model during the attribution. First, we introduce Concept Influence which attribute model behavior to semantic directions (such as linear probes or sparse autoencoder features) rather than individual test examples. Second, we show that simple probe-based attribution methods are first-order approximations of Concept Influence that achieve comparable performance while being over an order-of-magnitude faster. We empirically validate Concept Influence and approximations across emergent misalignment benchmarks and real post-training datasets, and demonstrate they achieve comparable performance to classical influence functions while being substantially more scalable. More broadly, we show that incorporating interpretable structure within traditional TDA pipelines can enable more scalable, explainable, and better control of model behavior through data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑