一个可组合的LLM可控生成工具包，支持四种控制方式。
AI Steerability 360: A Toolkit for Steering Large Language Models
- 提供输入、结构、状态、输出四类控制接口
- 支持多方法组合与任务级性能对比评估
- 开源易用，适合研究和应用开发
AI Steerability 360 是一个可扩展的开源 Python 工具包，用于控制大型语言模型。其控制机制围绕四个模型控制面设计：输入（修改提示）、结构（修改权重或架构）、状态（修改激活值与注意力）以及输出（修改解码过程）。所有控制方法通过统一接口——控制管道实现，并支持多方法组合。工具包内置用例类（定义任务）和基准类（在特定任务上比较性能），便于全面评估与对比。该工具显著降低开发与评估控制方法的门槛。工具包原生支持 Hugging Face，采用 Apache 2.0 许可证，开源地址为 https://github.com/IBM/AISteer360。
原文摘要 · Abstract (English)
The AI Steerability 360 toolkit is an extensible, open-source Python library for steering LLMs. Steering abstractions are designed around four model control surfaces: input (modification of the prompt), structural (modification of the model's weights or architecture), state (modification of the model's activations and attentions), and output (modification of the decoding or generation process). Steering methods exert control on the model through a common interface, termed a steering pipeline, which additionally allows for the composition of multiple steering methods. Comprehensive evaluation and comparison of steering methods/pipelines is facilitated by use case classes (for defining tasks) and a benchmark class (for performance comparison on a given task). The functionality provided by the toolkit significantly lowers the barrier to developing and comprehensively evaluating steering methods. The toolkit is Hugging Face native and is released under an Apache 2.0 license at https://github.com/IBM/AISteer360.
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。