Sell More, Play Less: Benchmarking LLM Realistic Selling Skill
Xuanbo Su, Wenhao Hu, Le Zhan, Yuting Xie, Kailin Lyu, Kaijie Chen, Ziwei Li, Yousong Wang 等 11 位
Chinese Academy of Sciences Institute of Automation Tongji University King Abdullah University of Science and Technology
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Sales dialogues require multi-turn, goaldirected persuasion under asymmetric incentives, which makes them a challenging setting for large language models (LLMs).Yet existing dialogue benchmarks rarely measure deal progression and outcomes.We introduce SalesLLM benchmark, a bilingual (ZH/EN) benchmark derived from realistic applications covering Financial Services and Consumer Goods, built from 30,074 scripted configurations and 1,805 curated multi-turn scenarios with controllable difficulty and personas.We propose a fully automatic evaluation pipeline that combines (i) an LLM judge for salesprocess progress, and (ii) fine-tuned BERT classifiers for end-of-dialogue buying intent.To improve simulation fidelity, we train a user model, CustomerLM, with SFT and DPO on 8,000+ crowdworker-involved sales conversations, reducing role inversion from 17.44% (GPT-4o) to 8.8%.SalesLLM benchmark scores correlate strongly with human ratings (average Pearson r = 0.86; inter-annotator agreement Krippendorff's α = 0.86, 500 annotations per model).Across 15 mainstream LLMs, in Chinese the strongest models are competitive with typical (junior-to-intermediate) human salespeoplenot with sales experts-while weaker ones fall below this baseline, and cross-lingual consistency remains poor.SalesLLM benchmark serves as a scalable benchmark for outcomeoriented sales agents.Our code and data are released at https://github.com/Bairong-X dynamics/Benchmarking-LLM-Realistic -Selling-Skill.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AISpeech and dialogue systems
AI in Service Interactions · Topic Modeling