arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2406.09702cs.CL
收藏

检测不需要事实判断的回复生成

Detecting Response Generation Not Requiring Factual Judgment

Tohoku University(东北大学);RIKEN(理化学研究所)

Ryohei Kamei, Daiki Shiono, Reina Akama, Jun Suzuki

AI总结:

本文提出识别对话中无需事实判断的句子,构建众包数据集DDFC并评估多类模型,最高分类准确率约88%,以兼顾回复吸引力与事实性。

摘要:

随着大型语言模型(LLM)的显著发展,确保输出的事实性已成为一项挑战。然而,在对话中,让回复的所有内容都具备给定知识或事实并不一定是好事。本研究旨在同时实现对话回复的吸引力与事实性,为此设定了一项任务:预测不需要事实正确性判断的句子,例如表示赞同或个人观点/感受的句子。我们通过众包为该任务创建了一个数据集,即带有事实核查需求标签的对话数据集(DDFC),并使用该数据集在若干模型上执行分类任务。分类准确率最高的模型可产生约88%的准确分类结果。

英文摘要:

With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge. However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in dialogues. This study aimed to achieve both attractiveness and factuality in a dialogue response for which a task was set to predict sentences that do not require factual correctness judgment such as agreeing, or personal opinions/feelings. We created a dataset, dialogue dataset annotated with fact-check-needed label (DDFC), for this task via crowdsourcing, and classification tasks were performed on several models using this dataset. The model with the highest classification accuracy could yield about 88% accurate classification results.

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。

↑