When humans solve complex problems, they typically create a sequence of ideas (involving an intuitive decision, reflection, error correction, etc.) in order to reach a conclusive decision. Contrary to this, today's models are mostly trained to map an input to one single and fixed output. In this paper, we investigate how we can give models the opportunity of a second, third and $k$-th thought. Taking inspiration from Hegel's dialectics, we propose the concept of a thought flow which creates a sequence of predictions. We present a self-correction mechanism that is trained to estimate the model's correctness and performs iterative prediction updates based on the correctness prediction's gradient. We introduce our method at the example of question answering and conduct extensive experiments that demonstrate (i) our method's ability to correct its own predictions and (ii) its potential to notably improve model performances. In addition, we conduct a qualitative analysis of thought flow correction patterns and explore how thought flow predictions affect human users within a crowdsourcing study. We find that (iii) thought flows enable improved user performance and are perceived as more natural, correct, and intelligent as single and/or top-3 predictions.

翻译：当人类解决复杂问题时，通常会形成一系列思路（涉及直觉判断、反思、纠错等）以达成最终决策。与此相反，当今的模型大多被训练为将输入映射为单一且固定的输出。本文探讨如何赋予模型产生第二、第三乃至第k次思考的机会。受黑格尔辩证法的启发，我们提出"思想流"概念，旨在生成预测序列。我们设计了一个自纠错机制，该机制经训练可评估模型正确性，并基于正确性预测的梯度执行迭代预测更新。我们以问答任务为例介绍该方法，并通过大量实验证明：（i）该方法具备自我修正预测的能力；（ii）其具有显著提升模型性能的潜力。此外，我们开展了思想流修正模式的定性分析，并通过众包研究探索思想流预测对人类用户的影响。研究发现：（iii）思想流能够提升用户表现，且相较于单次预测或top-3预测，其被认为更自然、更准确、更智能。