不要想白熊：认知负荷下Transformer模型中的讽刺性否定
Don't Think of the White Bear: Ironic Negation in Transformer Models Under Cognitive Load
AI总结：
该研究探讨Transformer模型在否定指令下的讽刺性反弹现象，通过两项实验分析认知负荷对反弹的影响及极性分离与反弹的关联，结合回路追踪揭示机制，并发布ReboundBench数据集支持后续研究。
摘要：
“不要提及X”这类否定指令会反常地增加X在人类思维中的可及性，这一现象被称为讽刺性反弹。大型语言模型（LLMs）面临同样挑战：抑制某个概念需要在内部激活它，这可能引发反弹而非避免。我们通过两项实验研究了这种张力。（1）负荷与内容：在给出否定指令后，我们改变干扰文本（语义型、句法型、重复型）并测量反弹强度。（2）极性分离：测试模型是否能区分同一概念的中性与否定框架，以及这种分离是否预测反弹的持续性。结果显示，否定后立即出现反弹且持续存在，更长或语义型干扰会加剧反弹，而重复干扰支持抑制。更强的极性分离与更持久的反弹相关。这些发现辅以回路追踪分析（识别出稀疏的中间层注意力头放大禁忌标记，而早期层则抑制），将讽刺性反弹的认知预测与长上下文干扰的机制见解联系起来。为支持未来研究，我们发布了ReboundBench数据集，包含5000个系统变化的否定提示，用于探测LLMs中的反弹现象。
英文摘要：
Negation instructions such as 'do not mention $X$' can paradoxically increase the accessibility of $X$ in human thought, a phenomenon known as ironic rebound. Large language models (LLMs) face the same challenge: suppressing a concept requires internally activating it, which may prime rebound instead of avoidance. We investigated this tension with two experiments. \textbf{(1) Load \& content}: after a negation instruction, we vary distractor text (semantic, syntactic, repetition) and measure rebound strength. \textbf{(2) Polarity separation}: We test whether models distinguish neutral from negative framings of the same concept and whether this separation predicts rebound persistence. Results show that rebound consistently arises immediately after negation and intensifies with longer or semantic distractors, while repetition supports suppression. Stronger polarity separation correlates with more persistent rebound. Together, these findings, complemented by a circuit tracing analysis that identifies sparse middle-layer attention heads amplifying forbidden tokens while early layers suppress, link cognitive predictions of ironic rebound with mechanistic insights into long-context interference. To support future work, we release ReboundBench, a dataset of $5,000$ systematically varied negation prompts designed to probe rebound in LLMs.
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。
