让大模型学会答同义问题，提升问答一致性。
RoParQ: Paraphrase-Aware Alignment of Large Language Models Towards Robustness to Paraphrased Questions
- 用改写问题构建评测集，筛选出答案不一致的样本。
- 新指标显示微调后小模型一致性媲美大模型。
- 基于推理的微调策略增强模型对语义的理解能力。
大型语言模型在回答同义问题时表现不一致，反映出其依赖表层模式而非真正语义理解。为此，我们提出 RoParQ，一个专用于评估闭卷多选题中跨同义问题一致性的基准。该基准通过专有模型生成问题改写，并保留使裁判模型产生不一致置信度的样本。我们还提出 XParaCon 评估指标，通过计算不同问题变体下准确率的标准差来量化模型鲁棒性。此外，我们设计了一种基于推理的、面向同义改写的监督微调策略，旨在使模型向语义不变性对齐。实验表明，这种针对性对齐显著提升了模型鲁棒性。值得注意的是，微调后的轻量级模型在一致性上达到与更大预训练模型相当的水平。结果证明该方法有效缓解了表层记忆问题，推动更稳健、可靠的 LLM 发展。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often exhibit inconsistent behavior when answering paraphrased questions, suggesting a reliance on surface-level patterns rather than true semantic understanding. To address this limitation, we introduce RoParQ, a benchmark specifically constructed to evaluate cross-paraphrase consistency in closed-book multiple-choice QA. This benchmark is derived from standard datasets by generating paraphrases via proprietary models and selectively retaining examples that elicit inconsistent confidence from a judge model. We further propose XParaCon, a novel evaluation metric that quantifies a model's robustness by measuring the standard deviation of accuracies across question variants. Additionally, we implement a reasoning-based, paraphrase-aware Supervised Fine-Tuning (SFT) strategy designed to align models toward semantic invariance. Our experiments demonstrate that this targeted alignment significantly enhances robustness. Notably, fine-tuned lightweight models achieved consistency levels comparable to much larger pre-trained models. These results highlight the efficacy of our approach in mitigating superficial memorization and fostering more robust, reliable LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。