dattri-LLM：一种用于在LLM规模上进行训练数据归因的统一且高效的库
dattri-LLM 是一个新库，通过提高效率和兼容性来解决在大规模语言模型中训练数据归属的挑战。
01
影响到谁
- 1dattri-LLM
- 使用 →事实
- 支撑 →事实
- 依赖 →事实
- 使用 →事实
- 使用 →事实
02
证据
- AarXiv cs.LG研究机构2026-10-02 12:00
Most scalable TDA methods rely on per-example gradients, whose computation and use at LLM scale pose challenges in efficiency, compatibility, and extensibility.
- AarXiv cs.LG研究机构2026-10-02 12:00
Abstract: Training data attribution (TDA) estimates the contribution of individual training examples to model outputs. Most scalable TDA methods rely on per-ex…