arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.06334cs.IRcs.AIcs.CL
收藏

ExaRanker-Open:使用开源大语言模型为信息检索生成合成解释

ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMs

FEEC, UNICAMP(坎皮纳斯州立大学电气工程与计算机科学学院);NeuralMind(NeuralMind公司)

Fernando Ferraretto, Thiago Laitz, Roberto Lotufo, Rodrigo Nogueira

AI总结:

本文提出 ExaRanker-Open,利用开源大语言模型生成合成解释来增强信息检索训练,实验表明该方法能持续提升神经排序器性能,且在大数据集上仍有效,并开源了代码和数据集。

摘要:

ExaRanker 最近引入了一种训练信息检索(IR)模型的方法,将自然语言解释作为附加标签。该方法解决了标记样本有限的问题,从而提高了信息检索模型的有效性。然而,最初的结果基于专有语言模型(如 GPT-3.5),由于其成本和数据隐私问题,对数据集规模造成了限制。在本文中,我们介绍了 ExaRanker-Open,在其中我们调整并探索使用开源语言模型来生成解释。该方法已使用不同的大语言模型(LLM)和数据集规模进行了测试,以更好地理解数据增强的有效贡献。我们的研究结果表明,加入解释能持续增强神经排序器,且随着 LLM 规模的增大,收益也随之增加。值得注意的是,数据增强方法即使在大数据集上也被证明是有利的,正如我们的研究中 ExaRanker 超过目标基线 0.6 个 nDCG@10 点所证明的那样。为了鼓励研究社区的进一步进展,我们已在 https://github.com/unicamp-dl/ExaRanker 开源了代码和数据集。

英文摘要:

ExaRanker recently introduced an approach to training information retrieval (IR) models, incorporating natural language explanations as additional labels. The method addresses the challenge of limited labeled examples, leading to improvements in the effectiveness of IR models. However, the initial results were based on proprietary language models such as GPT-3.5, which posed constraints on dataset size due to its cost and data privacy. In this paper, we introduce ExaRanker-Open, where we adapt and explore the use of open-source language models to generate explanations. The method has been tested using different LLMs and datasets sizes to better comprehend the effective contribution of data augmentation. Our findings reveal that incorporating explanations consistently enhances neural rankers, with benefits escalating as the LLM size increases. Notably, the data augmentation method proves advantageous even with large datasets, as evidenced by ExaRanker surpassing the target baseline by 0.6 nDCG@10 points in our study. To encourage further advancements by the research community, we have open-sourced both the code and datasets at https://github.com/unicamp-dl/ExaRanker.

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。

↑