arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.06559cs.CLcs.AIcs.LG
收藏

利用大型语言模型驾驭商业与媒体洞察

Harnessing Business and Media Insights with Large Language Models

Center for Advanced AI Accenture(埃森哲高级人工智能中心);Accenture(埃森哲);Fortune Media(财富媒体)
Yujia Bao, Ankit Parag Shah, Neeru Narang, Jonathan Rivers, Rajeev Maksey, Lan Guan, Louise N. Barrere, Shelley Evenson, Rahul Basole, Connie Miao, Ankit Mehta,… 展开作者

Yujia Bao, Ankit Parag Shah, Neeru Narang, Jonathan Rivers, Rajeev Maksey, Lan Guan, Louise N. Barrere, Shelley Evenson, Rahul Basole, Connie Miao, Ankit Mehta, Fabien Boulay, Su Min Park, Natalie E. Pearson, Eldhose Joy, Tiger He, Sumiran Thakur, Koustav Ghosal, Josh On, Phoebe Morrison, Tim Major, Eva Siqi Wang, Gina Escobar, Jiaheng Wei, Tharindu Cyril Weerasooriya, Queena Song, Daria Lashkevich, Clare Chen, Gyuhak Kim, Dengpan Yin, Don Hejna, Mo Nomeli, Wei Wei

AI总结:

本文提出面向商业与媒体领域的 FALM,通过专业新闻知识库、时间感知推理、主题趋势分析及内容引用与任务分解,提升商业问答和财务数据可视化的准确性与可信度。

摘要:

本文介绍了 Fortune Analytics Language Model(FALM)。FALM 让用户能够直接获取全面的商业分析,包括市场趋势、公司绩效指标和专家洞察。与通用 LLM 不同,FALM 利用由专业新闻构建的精选知识库,使其能够针对复杂商业问题给出精确而深入的回答。用户还可以借助自然语言查询直接可视化财务数据,生成富有洞察力的图表,以清晰理解不同商业部门的趋势。FALM 通过三种新方法培养用户信任并确保输出准确性:1)时间感知推理保证准确的事件登记,并优先考虑近期更新。2)主题趋势分析显式考察主题随时间的演变,提供对新兴商业格局的洞察。3)内容引用和任务分解增强答案保真度与数据可视化准确性。我们进行了自动评估和人工评估,结果表明 FALM 相较基线方法取得显著性能提升,同时优先践行负责任的 AI 实践。这些基准测试确立了 FALM 作为商业和媒体领域前沿 LLM 的地位,具有出色的准确性和可信度。

英文摘要:

This paper introduces Fortune Analytics Language Model (FALM). FALM empowers users with direct access to comprehensive business analysis, including market trends, company performance metrics, and expert insights. Unlike generic LLMs, FALM leverages a curated knowledge base built from professional journalism, enabling it to deliver precise and in-depth answers to intricate business questions. Users can further leverage natural language queries to directly visualize financial data, generating insightful charts and graphs to understand trends across diverse business sectors clearly. FALM fosters user trust and ensures output accuracy through three novel methods: 1) Time-aware reasoning guarantees accurate event registration and prioritizes recent updates. 2) Thematic trend analysis explicitly examines topic evolution over time, providing insights into emerging business landscapes. 3) Content referencing and task decomposition enhance answer fidelity and data visualization accuracy. We conduct both automated and human evaluations, demonstrating FALM's significant performance improvements over baseline methods while prioritizing responsible AI practices. These benchmarks establish FALM as a cutting-edge LLM in the business and media domains, with exceptional accuracy and trustworthiness.

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。

↑