量化懒惰、解码亚优性和上下文退化现象于大语言模型
Quantifying Laziness, Decoding Suboptimality, and Context Degradation in Large Language Models
AI总结：
研究量化了大语言模型在多部分指令中的懒惰、解码亚优性和上下文退化现象，发现模型在简单任务中表现稳健，但需通过自我完善和动态提示提升指令合规性。
摘要：
大语言模型（LLMs）常常表现出行为特征，如懒惰（响应提前截断或部分遵守多部分请求）、解码亚优性（由于短视解码未能选择高质量序列）和上下文退化（在长对话中遗忘或忽略核心指令）。我们进行了三个受控实验（A、B和C）来量化这些现象在几种先进LLMs（OpenAI GPT-4变种、DeepSeek）中的表现。我们的结果表明，在满足复杂多部分指令方面存在广泛的懒惰现象：模型经常省略所需部分或即使在明确提示下也未能满足长度要求。然而，我们在简单推理任务中发现了解码亚优性的有限证据（模型的贪心回答似乎与最高置信度解决方案一致），并在200轮混沌对话测试中观察到令人惊讶的上下文退化鲁棒性——模型在关键事实和指令的保持方面表现得比预期更好。这些发现表明，尽管遵守详细指令仍是一个开放性挑战，现代LLMs可能在简单检索场景中内部缓解了一些假设的失败模式（如上下文遗忘）。我们讨论了可靠性的影响，将我们的发现与先前关于指令遵循和长上下文处理的工作联系起来，并推荐策略（如自我完善和动态提示）以减少懒惰并增强多指令合规性。
英文摘要：
Large Language Models (LLMs) often exhibit behavioral artifacts such as laziness (premature truncation of responses or partial compliance with multi-part requests), decoding suboptimality (failure to select higher-quality sequences due to myopic decoding), and context degradation (forgetting or ignoring core instructions over long conversations). We conducted three controlled experiments (A, B, and C) to quantify these phenomena across several advanced LLMs (OpenAI GPT-4 variant, DeepSeek). Our results indicate widespread laziness in satisfying complex multi-part instructions: models frequently omitted required sections or failed to meet length requirements despite explicit prompting. However, we found limited evidence of decoding suboptimality in a simple reasoning task (the models' greedy answers appeared to align with their highest-confidence solution), and we observed surprising robustness against context degradation in a 200-turn chaotic conversation test - the models maintained key facts and instructions far better than expected. These findings suggest that while compliance with detailed instructions remains an open challenge, modern LLMs may internally mitigate some hypothesized failure modes (such as context forgetting) in straightforward retrieval scenarios. We discuss implications for reliability, relate our findings to prior work on instruction-following and long-context processing, and recommend strategies (such as self-refinement and dynamic prompting) to reduce laziness and bolster multi-instruction compliance.
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。
