Parallel LLM Reasoning for Bias-Resilient, Robust Conceptual Abstraction

并行大模型推理：实现抗偏见且稳健的概念抽象

Abstract: Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when analyzing long documents. When long documents are processed sequentially, early or dominant concepts can overshadow less visible but meaningful interpretations, leading to cumulative analytical bias, omission error, and over-generalization.

摘要： 大型语言模型（LLMs）正越来越多地被用于文本分析。然而，在分析长文档时，它们往往受到上下文推理局限性的困扰。当长文档被顺序处理时，早期或占主导地位的概念可能会掩盖那些不那么显眼但具有意义的解读，从而导致累积的分析偏差、遗漏错误和过度概括。

Additionally, independently generated outputs are often merged without systematic grounding, introducing redundancy, conceptual drift, and unsupported claims. This study proposes a structured framework combining parallel chunk-level processing with evidence-anchored consolidation.

此外，独立生成的输出往往在缺乏系统性依据的情况下被合并，从而引入了冗余、概念漂移和缺乏支持的论断。本研究提出了一个结构化框架，将并行分块处理与基于证据锚定的整合相结合。

Texts are first divided into semantically coherent chunks and processed independently in parallel to remove influence from earlier processing. The independently generated interpretations are then consolidated using explicit evidence anchoring and prioritization that reduces dominance and over-generalization while improving traceability.

文本首先被划分为语义连贯的块，并并行独立处理，以消除早期处理过程的影响。随后，利用明确的证据锚定和优先级排序对独立生成的解读进行整合，这不仅减少了主导性偏差和过度概括，还提高了可追溯性。

Experiments with multiple model types and sizes indicate that parallel processing significantly reduces omission error by approximately 84%, increases evidence traceability by up to 130%, and reduces unsupported claims by up to 91%. Smaller models benefited most, suggesting that efficient parallel chunking and consolidation play a critical role in achieving reliable and scalable textual analysis.

针对多种模型类型和规模的实验表明，并行处理可显著减少约 84% 的遗漏错误，将证据可追溯性提高多达 130%，并将缺乏支持的论断减少多达 91%。较小的模型受益最为显著，这表明高效的并行分块与整合在实现可靠且可扩展的文本分析中发挥着关键作用。