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 2606.03318cs.CL
收藏

超越理想指令:现实交互中评估大语言模型的综合框架

Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions

Department of Data Science, City University of Hong Kong(香港城市大学数据科学系);Hong Kong Institute of AI for Science, City University of Hong Kong(香港城市大学人工智能科学研究院);Li Auto Inc.(Li汽车公司);Beijing University of Posts and Telecommunications(北京邮电大学);Independent Researcher(独立研究员)

Xuan Yang, Hao Xu, Tingfeng Hui, Hongsheng Xin, Kaike Zhang, Chunxiao Liu, Ning Miao

AI总结:

提出RUT-Bench基准,通过高保真模拟理想与非理想用户行为,评估大语言模型在现实工具调用场景中的表现,发现所有测试模型成功率低于40%且面对复杂非理想输入时性能显著下降。

摘要:

尽管大语言模型(LLMs)在工具使用能力上取得了巨大进步,但现有的评估基准难以完全对齐真实世界场景。这些基准大多依赖于模拟的理想化用户假设,缺乏面向经验的评估。这些局限性未能考虑到真实用户特有的模糊性、不合作行为和意图转变。为填补这一空白,我们提出了RUT-Bench,一个专门用于评估LLMs在多样化真实用户工具调用场景下的基准。RUT-Bench支持高保真模拟,涵盖单轮和多轮对话中的理想理性模式和非理想异质行为。我们使用该基准对19个广泛采用的开源和专有LLMs进行了全面评估。实验结果显示,没有测试的LLM实现超过40%的整体成功率,并且几乎所有模型在面对更复杂的非理想用户输入时都经历了明显的性能下降。我们的代码和数据可在该https URL获取。

英文摘要:

Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world scenarios. Such benchmarks mostly rely on simulated idealized user assumptions and lacks experience-oriented evaluation. These limitations fail to account for the ambiguity, uncooperative behaviors, and shifting intentions characteristic of real-world users. To fill this gap, we propose RUT-Bench, a dedicated benchmark designed to assess LLMs under diverse Real-world User Tool calling scenarios. RUT-Bench supports high-fidelity simulations covering both ideal rational patterns and heterogeneous non-ideal behaviors across single-turn and multi-turn dialogues. We conduct comprehensive evaluations on 19 widely adopted open-source and proprietary LLMs using our benchmark. Experimental results reveal that no tested LLMs achieve an overall success rate above 40%, and nearly all of them experience noticeable performance drops when facing more complicated non-ideal user inputs. Our code and data is available at https://github.com/Miaow-Lab/RUT-Bench.

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。

↑