V-RECS：一个具备解释、字幕生成和建议的低成本 LLM4VIS 推荐器
V-RECS, a Low-Cost LLM4VIS Recommender with Explanations, Captioning and Suggestions
AI总结：
本文提出首个基于LLM的可视化推荐器V-RECS，通过GPT-4作为教师生成CoT指令微调Llama-2-7B，以低成本实现与GPT-4相当的性能，并提供解释、字幕生成和建议以辅助非专家用户的数据探索。
摘要：
NL2VIS（自然语言到可视化）是一个充满前景的新兴研究领域，涉及解释自然语言查询并将其转化为能准确表示底层数据的可视化。在大数据时代，NL2VIS 具有巨大的应用潜力，因为它极大地便利了非专家用户的数据探索。随着生成式 AI 在 NL2VIS 应用中的日益广泛使用，本文提出了 V-RECS，这是首个基于 LLM 的可视化推荐器，并增加了解释（E）、字幕生成（C）和建议（S）以进一步支持数据探索。V-RECS 的可视化叙述既能帮助非专家用户验证响应，又能促进数据探索。此外，我们提出的解决方案通过利用有效微调小模型的方法，缓解了与使用强大 LLM 相关的计算、可控性和成本问题。为了生成有深度的可视化叙述，我们使用了思维链，这是一种提示工程技术，可帮助 LLM 识别并生成产生正确答案的逻辑步骤。由于据报道 CoT 在小型 LLM 上表现不佳，我们采用了一种策略：由大型 LLM（GPT-4）作为教师，生成基于 CoT 的指令来微调扮演学生角色的小型模型 Llama-2-7B。基于 AI 可视化定量评估框架以及一组参与者人工评估的广泛实验表明，V-RECS 取得了与 GPT-4 相当的性能得分，且成本要低得多。未经微调的 Llama 在绝大多数测试用例中无法执行该任务，这一事实也证明了 V-RECS 师生范式的有效性。我们向可视化社区发布了 V-RECS，以在整个可视化生成过程中协助可视化设计人员。
英文摘要：
NL2VIS (natural language to visualization) is a promising and recent research area that involves interpreting natural language queries and translating them into visualizations that accurately represent the underlying data. As we navigate the era of big data, NL2VIS holds considerable application potential since it greatly facilitates data exploration by non-expert users. Following the increasingly widespread usage of generative AI in NL2VIS applications, in this paper we present V-RECS, the first LLM-based Visual Recommender augmented with explanations(E), captioning(C), and suggestions(S) for further data exploration. V-RECS' visualization narratives facilitate both response verification and data exploration by non-expert users. Furthermore, our proposed solution mitigates computational, controllability, and cost issues associated with using powerful LLMs by leveraging a methodology to effectively fine-tune small models. To generate insightful visualization narratives, we use Chain-of-Thoughts (CoT), a prompt engineering technique to help LLM identify and generate the logical steps to produce a correct answer. Since CoT is reported to perform poorly with small LLMs, we adopted a strategy in which a large LLM (GPT-4), acting as a Teacher, generates CoT-based instructions to fine-tune a small model, Llama-2-7B, which plays the role of a Student. Extensive experiments-based on a framework for the quantitative evaluation of AI-based visualizations and on manual assessment by a group of participants-show that V-RECS achieves performance scores comparable to GPT-4, at a much lower cost. The efficacy of the V-RECS teacher-student paradigm is also demonstrated by the fact that the un-tuned Llama fails to perform the task in the vast majority of test cases. We release V-RECS for the visualization community to assist visualization designers throughout the entire visualization generation process.
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。
