在SemEval-2026任务11中采用ITLC:为LLMs中的形式推理进行规范化和确定性解析
ITLC at SemEval-2026 Task 11: Normalization and Deterministic Parsing for Formal Reasoning in LLMs
AI总结:
本文提出通过显式结构抽象和确定性解析减少LLMs推理中的内容偏差,方法在SemEval-2026任务11中取得前五名,有效降低偏差并提供替代复杂微调的方案。
摘要:
大型语言模型在推理任务中受到内容效应的影响,特别是在多语言上下文中。我们介绍了一种新的方法,通过显式结构抽象将直言推论转换为规范的逻辑表示,并应用确定性解析以确定有效性。在SemEval-2026任务11多语言基准测试中评估,我们的方法在所有子任务中均取得前五名,显著减少了内容效应,并提供了一个与复杂微调或激活层干预相竞争的替代方案。
英文摘要:
Large language models suffer from content effects in reasoning tasks, particularly in multi-lingual contexts. We introduce a novel method that reduces these biases through explicit structural abstraction that transforms syllogisms into canonical logical representations and applies deterministic parsing to determine validity. Evaluated on the SemEval-2026 Task 11 multilingual benchmark, our approach achieves top-5 rankings across all subtasks while substantially reducing content effects and offering a competitive alternative to complex fine-tuning or activation-level interventions.
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。