GeoSteer: 通过潜在流形梯度实现忠实的思维链引导
GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients
AI总结：
GeoSteer通过学习高质量CoT轨迹的低维流形，利用梯度引导提升LLM中间推理质量，实验显示在GSM8k数据集上准确率和推理质量均显著提升。
摘要：
近年来，大型语言模型（LLMs）在推理能力方面取得了显著进展，例如思维链（CoT）。大多数方法依赖于CoT推理步骤。先前的研究表明，即使最终答案正确，LLMs也常常生成逻辑不一致的推理步骤。这些不一致会降低推理过程的可靠性。我们提出了GeoSteer，一种基于流形的框架，旨在提高中间推理的质量。该方法包括：（1）构建具有步骤级评分的CoT数据集；（2）训练变分自编码器（VAE）模型和质量估计模型，以学习高质量CoT轨迹的低维流形；（3）通过沿着学习到的流形沿梯度引导目标LLM的隐藏状态，使隐藏状态向高质量区域偏移。这最后一步使隐藏状态的引导成为可能，从而实现几何上一致的引导。在GSM8k数据集上进行了评估实验，使用Qwen3系列进行评估。我们使用两个指标评估性能：答案准确率和整体推理质量。与原始LLM相比，GeoSteer将准确率提高了0.9个点，平均将推理质量提高了4.5个点。这些结果表明，GeoSteer提供了一种有效且可控的机制，以提高LLM中间推理的质量。
英文摘要：
Recent advances in Large Language Models (LLMs) have demonstrated remarkable progress in their reasoning capabilities, such as Chain-of-Thought (CoT). Most approaches rely on CoT rationales. Previous studies have shown that LLMs often generate logically inconsistent reasoning steps even when their final answers are correct. These inconsistencies reduce the reliability of the reasoning process. We propose GeoSteer, a manifold-based framework that improves the quality of intermediate reasoning. The method consists of: (1) constructing a CoT dataset with step-level scores, (2) training a Variational Autoencoder (VAE) model and a quality estimation model to learn a low-dimensional manifold of high-quality CoT trajectories, and (3) steering hidden states of target LLMs toward higher-quality regions in the latent space. This last step enables steering of the hidden states by following gradients along the learned manifold. It facilitates geometrically coherent steering. Evaluation experiments were conducted on the GSM8k dataset using the Qwen3 series. We evaluated performance using two metrics: answer accuracy and overall reasoning quality. GeoSteer improved the accuracy by 0.9 points and enhanced the reasoning quality by 4.5 points on average, compared with those of original LLMs. These results indicate that GeoSteer improves an effective and controllable mechanism for improving the quality of intermediate reasoning in 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。
