用提示工程提升大模型识别政治偏见能力，效果媲美精调模型。
Navigating Nuance: In Quest for Political Truth
- 设计新提示策略，融入细微语义线索增强偏见识别。
- Llama-3(70B)在MBIB上表现接近最优的ConvBERT模型。
- 适合关注信息真实性与社会极化的研究者和实践者。
本研究探究了应对政治偏见上升的多种微妙动机。我们基于一种融合细微识别理由的新提示技术，评估了Llama-3（70B）语言模型在媒体偏见识别基准（MBIB）上的表现。结果凸显了检测政治偏见的挑战，并展示了迁移学习方法提升未来模型的潜力。通过该框架，Llama-3(70B)在MBIB上的表现可与监督训练且完全微调的ConvBERT模型相媲美，优于其他基线模型，是当前政治偏见任务的最佳表现。本研究为开发更鲁棒的遏制虚假信息与极化传播工具提供了支持。代码与数据集已公开于GitHub。
原文摘要 · Abstract (English)
This study investigates the several nuanced rationales for countering the rise of political bias. We evaluate the performance of the Llama-3 (70B) language model on the Media Bias Identification Benchmark (MBIB), based on a novel prompting technique that incorporates subtle reasons for identifying political leaning. Our findings underscore the challenges of detecting political bias and highlight the potential of transfer learning methods to enhance future models. Through our framework, we achieve a comparable performance with the supervised and fully fine-tuned ConvBERT model, which is the state-of-the-art model, performing best among other baseline models for the political bias task on MBIB. By demonstrating the effectiveness of our approach, we contribute to the development of more robust tools for mitigating the spread of misinformation and polarization. Our codes and dataset are made publicly available in github.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。