arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.18013cs.CL
收藏

学会但未表达:大型语言模型中的能力-表达脱节

Learned but Not Expressed: Capability-Expression Dissociation in Large Language Models

Independent Researcher(独立研究员)

Toshiyuki Shigemura

AI总结:

研究探讨了大型语言模型在特定条件下能重构训练数据内容,但无法在常规生成任务中表现的能力脱节现象,发现生成输出中未出现非因果解决方案框架。

摘要:

大型语言模型(LLMs)在特定诱发条件下能够重构和追溯其训练数据中的内容,但这种能力在标准生成情境中并不显现。本实证研究考察了300个提示-响应生成中非因果、非可实施的解决方案类型的表达情况。基于最近关于记忆连续性和对齐诱导的语篇先验的研究,我们记录了学习能力与表达输出之间的系统性脱节。在三种不同的LLM、十个任务场景以及创造性的叙事和实用性的建议情境中,生成输出中未出现非因果解决方案框架(0%,95%置信区间:[0%,1.2%]),尽管在条件提取下已验证了重构能力。这些发现挑战了训练数据存在直接预测输出概率的普遍假设,证明任务条件生成策略可以跨不同情境全面抑制学习内容。结果对理解生成动态、输出分布控制以及当代LLM的行为边界具有启示作用。

英文摘要:

Large language models (LLMs) demonstrate the capacity to reconstruct and trace learned content from their training data under specific elicitation conditions, yet this capability does not manifest in standard generation contexts. This empirical observational study examines the expression of non-causal, non-implementable solution types across 300 prompt-response generations spanning narrative and problem-solving task contexts. Drawing on recent findings regarding memorization contiguity and alignment-induced discourse priors, we document a systematic dissociation between learned capability and expressed output. Across three distinct LLMs, ten task scenarios, and both creative narrative and practical advisory contexts, we documented zero instances of non-causal solution frames in generated outputs (0%, 95% CI: [0%, 1.2%]), despite verified reconstruction capability under conditional extraction. These findings challenge the prevailing assumption that training data presence directly predicts output probability, demonstrating instead that task-conditioned generation policies can comprehensively suppress learned content across diverse contexts. The results offer implications for understanding generation dynamics, output distribution control, and the behavioral boundaries of contemporary 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。

↑