幻觉能否有用？通过链式系统I/II推理用SLM解决多跳问题
Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoning
AI总结：
提出一种“先回答后推理”的认知启发框架，利用SLM的初始答案（可能包含幻觉）作为假设来检索证据，再通过系统II深度推理，从而在多跳问答任务上超越传统的“先思考后检索”方法。
摘要：
最近，小型语言模型（SLM）引起了越来越多的兴趣，它们速度快、性能好，且硬件需求低于大型语言模型（LLM）。然而，SLM比LLM更容易产生幻觉，影响其解决复杂多步推理问题的能力，因为早期错误会级联到最终响应。为了解决这个问题，现有工作采用先思考后迭代检索的策略来减少幻觉。我们认为先思考策略并非总是必要，因为我们发现：（i）SLM通常对其初始答案有准确的置信度，并且（ii）幻觉实际上可能有助于逼近正确答案。因此，我们将我们的工作定位为这种策略的反转，即先回答后推理。我们提出了一个认知启发的框架，其中模型首先被允许快速回答问题（系统I（零样本）），然后基于从知识源使用初始假设检索到的证据进行更深层次的思考（系统II）。通过结合系统I和系统II风格的推理，我们展示了我们的方法在各种多步问答基准测试中可以优于先前采用传统先思考路径的工作。
英文摘要：
Recently, there has been increased interest in Small Language Models (SLMs), which are fast, show good performance, and have lower hardware demands than large language models (LLMs). However, SLMs hallucinate more frequently than LLMs, impacting their ability to solve complex multi-step reasoning problems as early mistakes cascade to the final response. To address this, existing works think-first followed by iterative retrieval to reduce hallucination. We argue that the think-first strategy is not always necessary as we find that: (i) SLMs are often accurately confident in their initial answer and, (ii) hallucinations can actually be beneficial for honing in on the true answer. As such, we position our work as an inversion of this strategy, i.e., answer first-reason later. We propose a cognitively-inspired framework where the model is first allowed to quickly answer the question (System-I (zero-shot)) and then resorts to deeper thinking (System-II) based on evidence retrieved from a knowledge source using the initial hypothesis. By combining System-I and System-II style thinking, we show that our method can outperform prior work that takes the traditional think-first route on various multi-step question-answering benchmarks.
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。
