应对大型语言模型中的刻板印象：一种批判性审视与缓解
Addressing Stereotypes in Large Language Models: A Critical Examination and Mitigation
AI总结：
本文探讨了大型语言模型中的刻板印象问题，通过评估不同模型的偏见表现，提出增强学习策略以提升模型性能和减少偏见输出。
摘要：
大型语言模型（LLMs），如ChatGPT，近年来在自然语言处理（NLP）技术的进步推动下获得了广泛 popularity，其应用范围涵盖了许多学科和日常生活。LLMs 从训练数据中继承了显性和隐性的偏见；这些偏见可能包括社会、伦理、文化、宗教和其他偏见和刻板印象。通过识别这些缺陷的存在和程度，明确其来源，并尝试缓解这些偏见输出，以确保公平输出，减少有害刻板印象和虚假信息至关重要。本研究审视并强调在生成式人工智能（AI）日益增长的背景下，解决LLMs中的偏见的必要性。我们利用针对偏见的基准测试（如StereoSet和CrowSPairs）来评估许多不同生成模型（如BERT、GPT 3.5和ADA）中各种偏见的存在情况。为了检测显性和隐性偏见，我们采用了三重方法进行彻底和包容性的分析。结果表明，微调模型在性别偏见方面表现不佳，但在识别和避免种族偏见方面表现优异。我们的发现还表明，尽管在某些情况下取得了成功，但LLMs往往过度依赖提示中的关键词，这表明LLMs无法真正尝试理解其输出的准确性和真实性。最后，为了提升模型性能，我们应用了一种增强学习策略，包括微调、使用不同提示技术的模型以及偏见基准的数据增强。我们发现微调模型在跨数据集测试中表现出有希望的适应性，并在隐性偏见基准上显著提高了性能，性能提升高达20%。
英文摘要：
Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and implicit biases from the datasets they were trained on; these biases can include social, ethical, cultural, religious, and other prejudices and stereotypes. It is important to comprehensively examine such shortcomings by identifying the existence and extent of such biases, recognizing the origin, and attempting to mitigate such biased outputs to ensure fair outputs to reduce harmful stereotypes and misinformation. This study inspects and highlights the need to address biases in LLMs amid growing generative Artificial Intelligence (AI). We utilize bias-specific benchmarks such StereoSet and CrowSPairs to evaluate the existence of various biases in many different generative models such as BERT, GPT 3.5, and ADA. To detect both explicit and implicit biases, we adopt a three-pronged approach for thorough and inclusive analysis. Results indicate fine-tuned models struggle with gender biases but excel at identifying and avoiding racial biases. Our findings also illustrated that despite some cases of success, LLMs often over-rely on keywords in prompts and its outputs. This demonstrates the incapability of LLMs to attempt to truly understand the accuracy and authenticity of its outputs. Finally, in an attempt to bolster model performance, we applied an enhancement learning strategy involving fine-tuning, models using different prompting techniques, and data augmentation of the bias benchmarks. We found fine-tuned models to exhibit promising adaptability during cross-dataset testing and significantly enhanced performance on implicit bias benchmarks, with performance gains of up to 20%.
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。
