发现裂缝：通过反语探测和一致性验证改进大语言模型推理
Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verification
AI总结：
PPCV通过反语探测和一致性验证改进大语言模型推理，通过识别和替换关键标记以提升推理准确性。
摘要：
大型语言模型在各种推理任务中展示了出色的性能。然而，它们在更复杂的任务上的问题解决能力往往会因幻觉和中间步骤中错误的累积而下降。最近的研究引入了
英文摘要：
Large language models have demonstrated impressive performance across a variety of reasoning tasks. However, their problem-solving ability often declines on more complex tasks due to hallucinations and the accumulation of errors within these intermediate steps. Recent work has introduced the notion of critical tokens--tokens in the reasoning process that exert significant influence on subsequent steps. Prior studies suggest that replacing critical tokens can refine reasoning trajectories. Nonetheless, reliably identifying and exploiting critical tokens remains challenging. To address this, we propose the Paraphrastic Probing and Consistency Verification~(PPCV) framework. PPCV operates in two stages. In the first stage, we roll out an initial reasoning path from the original question and then concatenate paraphrased versions of the question with this reasoning path. And we identify critical tokens based on mismatches between the predicted top-1 token and the expected token in the reasoning path. A criterion is employed to confirm the final critical token. In the second stage, we substitute critical tokens with candidate alternatives and roll out new reasoning paths for both the original and paraphrased questions. The final answer is determined by checking the consistency of outputs across these parallel reasoning processes. We evaluate PPCV on mainstream LLMs across multiple benchmarks. Extensive experiments demonstrate PPCV substantially enhances the reasoning performance of LLMs compared to baselines.
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。
