SPOT:基于跨度的思考暂停,用于大语言模型中高效且可解释的潜在推理
SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models
AI总结:
SPOT通过压缩显式推理步骤为紧凑的潜在暂停token,提升大语言模型的推理效率和可解释性。
摘要:
显式链式推理提高了大语言模型的推理性能,但通常由于冗长的逐token追踪而带来高推理成本。尽管近期方法通过简洁提示或步骤剪枝减少了这种开销,但它们大多截断了模型所说的内容,而不是内部化模型的思考过程。潜在推理提供了一种有前途的替代方法,通过在隐藏空间中执行计算,但先前方法面临两个关键挑战。许多现有方法依赖于刚性的点对点对齐,迫使潜在token近似推理步骤的最终表示,这可能不足以捕捉整个推理段落的密集、可变长度语义。此外,这些方法常常缺乏可解释性:潜在状态通常由无约束优化或嵌入混合产生,导致难以解码或审计的向量。我们提出了SPOT,一个灵活的框架,将显式的CoT压缩成紧凑的潜在暂停token,而无需强制使用固定的响应模板。SPOT的核心是跨度级语义对齐,一个Sinkhorn最优传输目标,使每个暂停token柔和地匹配整个推理段落的语义,克服了步骤结束对齐的刚性。为进一步提高可解释性,SPOT引入了冻结头解码约束,使潜在状态能够在冻结的预训练LM头下直接解码为token分布,使潜在思考的关键词解释变得可读。在推理基准测试中,SPOT在准确性上平均提高了2.3个点,同时减少了生成token的37.5%,并提供了对潜在推理过程的忠实语义解释。
英文摘要:
Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step pruning, they largely truncate what the model says rather than internalize what the model thinks. Latent reasoning offers a promising alternative by performing computation in the hidden space, yet prior methods face two critical challenges. Many existing approaches rely on rigid point-to-point alignment, forcing a latent token to approximate the final representation of a reasoning step, which can be insufficient to capture the dense, variable-length semantics of an entire reasoning segment. Furthermore, these methods often suffer from a lack of interpretability: latent states are commonly produced by unconstrained optimization or embedding mixing, yielding vectors that are difficult to decode or audit under the pretrained language head. We propose SPOT, a flexible framework that compresses explicit CoT into compact latent pause tokens without enforcing a fixed response template. At the core of SPOT is Span-level Semantic Alignment, a Sinkhorn optimal-transport objective that softly matches each pause token to the semantics of an entire reasoning segment, overcoming the rigidity of step-end alignment. To further improve interpretability, SPOT introduces a Frozen-Head Decoding Constraint that keeps latent states directly decodable as token distributions under the frozen pretrained LM head, enabling readable keyword interpretations of latent thoughts. Experiments on reasoning benchmarks demonstrate that SPOT improves accuracy by 2.3 points on average while reducing generated tokens by 37.5% and provides faithful semantic interpretations of the latent reasoning process.
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。