优化推理的o1模型仍受概率敏感性影响，未完全摆脱自回归痕迹。
When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1
- 通过思维链优化推理能力，提升罕见任务表现
- 高概率任务下减少思考步骤，低概率任务效果下降
- 适合研究模型本质局限与推理优化边界的研究者
在《自回归余烬》（McCoy et al., 2023）中，我们指出多个大语言模型（LLMs）的重要局限源于其作为下一词预测模型的起源。本文研究OpenAI新推出的o1系统——该系统不同于以往模型，专为推理优化。结果发现，o1在多数情况下显著优于先前模型，尤其在常见任务的罕见变体上表现突出（如从每词第二个字母构成缩写，而非首字母）。然而，尽管有量级提升，o1仍表现出与旧系统相同的定性趋势：对示例和任务的概率敏感，在高概率情境下表现更优且所需‘思考令牌’更少。这表明，推理优化可缓解但未必彻底克服语言模型的概率敏感性。
原文摘要 · Abstract (English)
In "Embers of Autoregression" (McCoy et al., 2023), we showed that several large language models (LLMs) have some important limitations that are attributable to their origins in next-word prediction. Here we investigate whether these issues persist with o1, a new system from OpenAI that differs from previous LLMs in that it is optimized for reasoning. We find that o1 substantially outperforms previous LLMs in many cases, with particularly large improvements on rare variants of common tasks (e.g., forming acronyms from the second letter of each word in a list, rather than the first letter). Despite these quantitative improvements, however, o1 still displays the same qualitative trends that we observed in previous systems. Specifically, o1 -- like previous LLMs -- is sensitive to the probability of examples and tasks, performing better and requiring fewer "thinking tokens" in high-probability settings than in low-probability ones. These results show that optimizing a language model for reasoning can mitigate but might not fully overcome the language model's probability sensitivity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。