神经检索器对LLM生成内容存在偏向
Neural Retrievers are Biased Towards LLM-Generated Content
AI总结：
本文首次定量揭示神经检索与重排序模型对LLM生成内容存在系统性来源偏向，并从文本压缩角度解释成因，提出即插即用去偏约束，同时发布两个新基准以警示IR社区。
摘要：
近年来，大语言模型（LLMs）的出现彻底改变了信息检索（IR）应用的范式，尤其是在网络搜索领域，LLMs在互联网上生成了大量类人文本。因此，LLM时代的IR系统正面临一个新挑战：索引文档现在不仅由人类撰写，还由LLMs自动生成。这些LLM生成的文档如何影响IR系统是一个紧迫且尚未被探索的问题。在这项工作中，我们对同时涉及人类撰写和LLM生成文本的场景中的IR模型进行了定量评估。令人惊讶的是，我们的研究结果表明，神经检索模型倾向于将LLM生成的文档排在更高的位置。我们将神经检索器对LLM生成内容的这类偏向称为“来源偏向”。此外，我们发现这种偏向不仅限于第一阶段的神经检索器，还延伸到第二阶段的神经重排序器。随后，从文本压缩角度的深入分析表明，LLM生成的文本表现出更集中的语义和更少的噪声，使神经检索模型更容易进行语义匹配。为了缓解来源偏向，我们还提出了一种即插即用的去偏约束用于优化目标，实验结果表明了其有效性。最后，我们讨论了由观察到的来源偏向可能引发的严重问题，并希望我们的发现能够成为对IR社区及其他领域的重要警示。为了促进LLM时代IR的未来探索，我们构建的两个新基准已在 https://github.com/KID-22/Source-Bias 上公开。
英文摘要：
Recently, the emergence of large language models (LLMs) has revolutionized the paradigm of information retrieval (IR) applications, especially in web search, by generating vast amounts of human-like texts on the Internet. As a result, IR systems in the LLM era are facing a new challenge: the indexed documents are now not only written by human beings but also automatically generated by the LLMs. How these LLM-generated documents influence the IR systems is a pressing and still unexplored question. In this work, we conduct a quantitative evaluation of IR models in scenarios where both human-written and LLM-generated texts are involved. Surprisingly, our findings indicate that neural retrieval models tend to rank LLM-generated documents higher. We refer to this category of biases in neural retrievers towards the LLM-generated content as the \textbf{source bias}. Moreover, we discover that this bias is not confined to the first-stage neural retrievers, but extends to the second-stage neural re-rankers. Then, in-depth analyses from the perspective of text compression indicate that LLM-generated texts exhibit more focused semantics with less noise, making it easier for neural retrieval models to semantic match. To mitigate the source bias, we also propose a plug-and-play debiased constraint for the optimization objective, and experimental results show its effectiveness. Finally, we discuss the potential severe concerns stemming from the observed source bias and hope our findings can serve as a critical wake-up call to the IR community and beyond. To facilitate future explorations of IR in the LLM era, the constructed two new benchmarks are available at https://github.com/KID-22/Source-Bias.
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。
