arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.20179cs.CLcs.AIcs.RO
收藏

Robo-Instruct:用于微调代码LLM的仿真器增强指令对齐

Robo-Instruct: Simulator-Augmented Instruction Alignment For Finetuning Code LLMs

Zichao Hu, Junyi Jessy Li, Arjun Guha, Joydeep Biswas

AI总结:

本文提出ROBO-INSTRUCT框架,通过在程序执行期间动态合成任务特定仿真环境并集成LLM辅助的指令后处理,高效微调小型专用代码LLM,使其在机器人任务上超越基线并媲美更大规模专有模型。

摘要:

代码LLM在将自然语言转换任务转换为可由服务机器人执行的程序方面展现了可喜的成果。我们有兴趣为此微调小型专用LLM,但收集特定于每个机器人的任务-程序对数据集既耗时又昂贵。虽然SELF-INSTRUCT和EVOL-INSTRUCT等方法能够在给定少量示例的情况下生成新任务,但它们无法使用提供的编程接口提供正确遵守物理世界和机器人约束的相应程序。使用仿真器是检查此类约束的自然潜在解决方案,但构建能够处理任意任务及其必要对象和位置的仿真环境具有挑战性。为了应对这些挑战,我们引入了ROBO-INSTRUCT,它通过在任务程序中根据实体的使用方式机会性地推断实体属性并强制执行相应约束,在程序执行期间动态合成特定于任务的仿真环境。此外,ROBO-INSTRUCT集成了LLM辅助的后处理程序,以优化指令从而更好地与机器人程序对齐。我们在多个LLM上展示了ROBO-INSTRUCT的有效性,表明我们微调的模型优于所有基线方法,甚至匹配或超越了几种更大和专有模型的性能。

英文摘要:

Code LLMs have shown promising results with converting tasks in natural language to programs that can be executed by service robots. We are interested in finetuning small, specialized LLMs for this purpose, but collecting datasets of task-program pairs specific to each robot is time-consuming and expensive. While approaches such as SELF-INSTRUCT and EVOL-INSTRUCT are capable of generating novel tasks given a few examples, they are unable to provide the corresponding programs that correctly abide by physical-world and robot-constraints using the provided programming interface. Using a simulator is a natural potential solution to checking for such constraints, but building simulation environments that can handle arbitrary tasks and their necessary objects and locations, is challenging. To address these challenges, we introduce ROBO-INSTRUCT, which synthesizes task-specific simulation environments on the fly during program execution, by opportunistically inferring entity properties and enforcing corresponding constraints based on how the entities are used in the task program. Additionally, ROBO-INSTRUCT integrates an LLM-aided post-processing procedure to refine instructions for better alignment with robot programs. We demonstrate the effectiveness of ROBO-INSTRUCT across multiple LLMs, showing that our fine-tuned models outperform all baseline methods and even match or surpass the performance of several larger and proprietary models.

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。

↑