潜在推理模型中的涌现搜索与回溯
Emergent Search and Backtracking in Latent Reasoning Models
AI总结：
研究发现潜在推理模型在无词推理中自发学习结构化搜索过程，通过回溯提升准确率并适应性地调整探索路径。
摘要：
当语言模型在没有词语的情况下进行推理时会发生什么？标准的推理LLM通过思维链来口头化中间步骤；潜在推理变换器（LRTs）则完全在连续隐藏空间中进行推理。我们研究了一个LRT，在多个选择型问答基准上解码模型在每一步中演变的信念。我们发现，模型自发地在潜在空间中学习了一种结构化的搜索过程。推理遵循一致的轨迹：一个探索阶段，概率质量在候选者之间扩散，对领先者暂时承诺，以及要么收敛或回溯。回溯很普遍（32%的实例），有益（非回溯实例的准确率提升34%），且主要朝着语义上最近的干扰项远离正确答案的方向。搜索是适应性的：用不可信的替代品替换干扰项可使探索缩短54%。潜在推理模型在激活空间中实现了思维链通过词语所实现的能力：能够犯错、察觉并恢复。
英文摘要：
What happens when a language model thinks without words? Standard reasoning LLMs verbalize intermediate steps as chain-of-thought; latent reasoning transformers (LRTs) instead perform deliberation entirely in continuous hidden space. We investigate an LRT, decoding the model's evolving beliefs at every step on a multiple-choice QA benchmark. We find that the model spontaneously learns a structured search process in latent space. Deliberation follows a consistent trajectory: an exploration phase where probability mass spreads across candidates, tentative commitment to a frontrunner, and either convergence or backtracking. Backtracking is prevalent (32% of instances), beneficial (34% accuracy gain over non-backtracking instances), and predominantly directed away from the semantically closest distractor toward the correct answer. The search is adaptive: replacing distractors with implausible alternatives shortens exploration by 54%. Latent reasoning models achieve in activation space what chain-of-thought achieves through words: the ability to be wrong, notice, and recover.
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。
