用神经符号AI提升大模型生成内容的可追溯性与可信度
Neurosymbolic AI approach to Attribution in Large Language Models
- 融合神经网络与符号推理，实现可解释的动态推理
- 解决现有方法中幻觉、偏见和来源不可靠的问题
- 适合需高可信度输出的研究与应用领域
大语言模型（LLMs）中的归因问题仍具挑战性，尤其在保障生成内容的事实准确性与可靠性方面。当前如Perplexity.ai和集成Bing搜索的LLM所采用的引用方法，虽通过实时搜索结果提供溯源信息，但仍存在幻觉、偏见、表面相关性匹配以及管理海量无过滤知识源的复杂性等问题。这些工具常依赖博客等不一致来源，影响整体可靠性。本文提出通过整合神经符号AI（NesyAI），结合神经网络的灵活性与符号推理的结构化优势，实现透明、可解释且动态的推理过程，从而缓解现有归因方法的局限。该研究探索了NesyAI框架如何增强现有归因模型，构建更可靠、可解释且适应性强的LLM系统。
原文摘要 · Abstract (English)
Attribution in large language models (LLMs) remains a significant challenge, particularly in ensuring the factual accuracy and reliability of the generated outputs. Current methods for citation or attribution, such as those employed by tools like Perplexity.ai and Bing Search-integrated LLMs, attempt to ground responses by providing real-time search results and citations. However, so far, these approaches suffer from issues such as hallucinations, biases, surface-level relevance matching, and the complexity of managing vast, unfiltered knowledge sources. While tools like Perplexity.ai dynamically integrate web-based information and citations, they often rely on inconsistent sources such as blog posts or unreliable sources, which limits their overall reliability. We present that these challenges can be mitigated by integrating Neurosymbolic AI (NesyAI), which combines the strengths of neural networks with structured symbolic reasoning. NesyAI offers transparent, interpretable, and dynamic reasoning processes, addressing the limitations of current attribution methods by incorporating structured symbolic knowledge with flexible, neural-based learning. This paper explores how NesyAI frameworks can enhance existing attribution models, offering more reliable, interpretable, and adaptable systems for LLMs.
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。