arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.03246cs.CL
收藏

让长上下文语言模型成为更好的多跳推理器

Making Long-Context Language Models Better Multi-Hop Reasoners

The Chinese University of Hong Kong(香港中文大学);Shanghai AI Laboratory(上海人工智能实验室)

Yanyang Li, Shuo Liang, Michael R. Lyu, Liwei Wang

AI总结:

本文提出 Reasoning with Attributions 方法,通过让语言模型在推理时为每个断言提供归因,并辅以归因标注数据集和专门微调策略,有效提升了长上下文语言模型在噪声环境下的多跳推理性能。

摘要:

长上下文建模的最新进展增强了语言模型(LMs)在多个自然语言处理应用中的复杂任务处理能力。尽管取得了这些进展,我们发现这些模型在多跳推理方面仍然存在困难,并且在存在噪声上下文时性能下降。在本文中,我们提出了 Reasoning with Attributions,这是一种新颖的方法,促使语言模型在推理过程中为每个断言提供归因。我们通过在三个多跳数据集上进行实验验证了该方法,使用了专有模型和开源模型,并证明了其有效性和鲁棒性。此外,我们探索了通过微调来增强推理能力的方法,并提供了一个带有归因标注的数据集和专门的训练策略。我们微调后的模型在多跳推理基准上取得了具有竞争力的性能,与 ChatGPT 和 Claude-instant 等专有语言模型的表现非常接近。

英文摘要:

Recent advancements in long-context modeling have enhanced language models (LMs) for complex tasks across multiple NLP applications. Despite this progress, we find that these models struggle with multi-hop reasoning and exhibit decreased performance in the presence of noisy contexts. In this paper, we introduce Reasoning with Attributions, a novel approach that prompts LMs to supply attributions for each assertion during their reasoning. We validate our approach through experiments on three multi-hop datasets, employing both proprietary and open-source models, and demonstrate its efficacy and resilience. Furthermore, we explore methods to augment reasoning capabilities via fine-tuning and offer an attribution-annotated dataset and a specialized training strategy. Our fine-tuned model achieves competitive performance on multi-hop reasoning benchmarks, closely paralleling proprietary LMs such as ChatGPT and Claude-instant.

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。

↑