包含思维：通过净化决策空间缓解偏好不稳定性
Inclusion-of-Thoughts: Mitigating Preference Instability via Purifying the Decision Space
AI总结：
提出包含思维（IoT）策略，通过逐步自过滤干扰选项来重构多选题，从而稳定模型偏好并提升推理性能。
摘要：
多项选择题（MCQ）被广泛用于评估大型语言模型（LLM）。然而，LLM 仍然容易受到似是而非的干扰项的影响。这常常将注意力转移到无关选项上，导致在正确和错误答案之间不稳定地摇摆。在本文中，我们提出包含思维（IoT），一种渐进式自过滤策略，旨在减轻这种认知负荷（即干扰项存在下模型偏好的不稳定性），并使模型更有效地关注合理答案。我们的方法仅使用合理的选项选择来重构 MCQ，为检查比较判断以及模型在扰动下内部推理的稳定性提供了一个受控环境。通过明确记录这一过滤过程，IoT 还增强了模型决策的透明度和可解释性。广泛的实证评估表明，IoT 在算术、常识推理和教育基准测试中显著提升了思维链性能，且计算开销极小。
英文摘要：
Multiple-choice questions (MCQs) are widely used to evaluate large language models (LLMs). However, LLMs remain vulnerable to the presence of plausible distractors. This often diverts attention toward irrelevant choices, resulting in unstable oscillation between correct and incorrect answers. In this paper, we propose Inclusion-of-Thoughts (IoT), a progressive self-filtering strategy that is designed to mitigate this cognitive load (i.e., instability of model preferences under the presence of distractors) and enable the model to focus more effectively on plausible answers. Our method operates to reconstruct the MCQ using only plausible option choices, providing a controlled setting for examining comparative judgements and therefore the stability of the model's internal reasoning under perturbation. By explicitly documenting this filtering process, IoT also enhances the transparency and interpretability of the model's decision-making. Extensive empirical evaluation demonstrates that IoT substantially boosts chain-of-thought performance across a range of arithmetic, commonsense reasoning, and educational benchmarks with minimal computational overhead.
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。
