言行不一：大型语言模型中的指令诱导冲突
Do as I Say, Not as I Do: Instruction-Induction Conflict in LLMs
AI总结：
研究探讨了大型语言模型在面对指令与模式完成之间的冲突时的表现，发现指令遵循率在不同模型和指令下差异显著，输出多样性是预测鲁棒性的主要因素。
摘要：
语言模型被训练以遵循指令，但它们也是强大的模式完成器。当这些两个目标发生冲突时会发生什么？我们构建了对话，其中用户指令要求以目标方式T（例如始终输出特定标记、用特定语言回答或采用特定角色）行为，与N个硬编码助手回合展示的竞争对手模式P相冲突。然后我们测量在此设置下的指令遵循率（IF率），在13个模型和16种不同指令上，最多50回合。平均指令遵循率在模型之间从1%到99%不等，与标准能力基准 largely 无关。从指令遵循到模式遵循的转变是普遍的但高度模型依赖的。鲁棒性由指令内容调节，当指令与训练价值先验一致时，模型对诱导的抵抗更长；同时由输出格式调节，多样化的多标记响应比单标记输出更耐受。链式推理提高鲁棒性但不消除易受性，并可能导致正确推理与错误输出之间的脱节。当被要求预测其在此设置下的行为时，模型平均准确率为83.5%，但系统性低估了自身对诱导压力的抵抗力。这些结果表明，即使对于其他方面能力较强的模型，指令遵循在诱导压力下仍很脆弱，而输出多样性而非输入的语义参与是预测鲁棒性的主要因素。
英文摘要：
Language models are trained to follow instructions, but they are also powerful pattern completers. What happens when these two objectives conflict? We construct conversations in which a user instruction to behave in a target way T (e.g., always output a specific token, answer in a particular language, or adopt a persona) is opposed by N hardcoded assistant turns demonstrating a competing pattern P. We then measure instruction-following (IF) rates in this setting, across 13 models and 16 different instructions, for up to 50 turns. Average instruction-following rates range from 1% to 99% across models, largely uncorrelated with standard capability benchmarks. The transition from instruction-following to pattern-following is universal but highly model-dependent. Robustness is modulated both by instruction content, with models resisting induction longer when instructions align with their trained value priors, and by output format, with diverse multi-token responses proving substantially more resistant than single-token outputs. Chain-of-thought reasoning improves robustness but does not eliminate susceptibility, and can produce dissociation between correct deliberation and incorrect output. When asked to predict their behavior in this setting, models achieve 83.5% accuracy on average but systematically underestimate their own resistance to induction pressure. These results suggest that instruction-following remains brittle under induction pressure even for otherwise capable models, and that output diversity, rather than semantic engagement with the input, is the primary factor predicting robustness.
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。
