基于提示的人格画像：用于相关性过滤的强化学习
Prompt-based Personality Profiling: Reinforcement Learning for Relevance Filtering
AI总结：
提出基于强化学习优化的相关性过滤方法，利用大模型零样本能力筛选相关内容，在缩短上下文的同时显著提升了人格特质预测的准确率。
摘要：
作者画像任务旨在通过分析个体分享的内容来推断其特征。尽管提示大型语言模型以解决自然语言理解任务已十分流行，但监督机器学习依然主导着执行该任务的自动系统。原因之一是分类实例包含大量帖子，可能是整个用户资料，这可能超出Transformers的输入长度。即使模型能使用大的上下文窗口，全部帖子也使得应用API访问的黑盒系统既昂贵又缓慢，此外还有此类“大海捞针”任务带来的问题。为缓解这一限制，我们提出一种新的作者画像方法，旨在首先区分相关与不相关内容，随后仅使用相关数据进行实际用户画像。为规避对相关性标注数据的需求，我们通过强化学习优化此相关性过滤器，其奖励函数利用大型语言模型的零样本能力。我们在两个Twitter语料库上评估了该方法对Big Five人格特质预测的效果。在标签分布偏斜的公开真实世界数据上，该方法显示出与使用用户资料中所有帖子相似的有效性，但上下文短得多。在对用人工帖子平衡的这些数据版本进行的评估中，对相关帖子的过滤使预测准确率显著提高。
英文摘要：
Author profiling is the task of inferring characteristics about individuals by analyzing content they share. Supervised machine learning still dominates automatic systems that perform this task, despite the popularity of prompting large language models to address natural language understanding tasks. One reason is that the classification instances consist of large amounts of posts, potentially a whole user profile, which may exceed the input length of Transformers. Even if a model can use a large context window, the entirety of posts makes the application of API-accessed black box systems costly and slow, next to issues which come with such "needle-in-the-haystack" tasks. To mitigate this limitation, we propose a new method for author profiling which aims at distinguishing relevant from irrelevant content first, followed by the actual user profiling only with relevant data. To circumvent the need for relevance-annotated data, we optimize this relevance filter via reinforcement learning with a reward function that utilizes the zero-shot capabilities of large language models. We evaluate our method for Big Five personality trait prediction on two Twitter corpora. On publicly available real-world data with a skewed label distribution, our method shows similar efficacy to using all posts in a user profile, but with a substantially shorter context. An evaluation on a version of these data balanced with artificial posts shows that the filtering to relevant posts leads to a significantly improved accuracy of the predictions.
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。
