用科学模拟器增强大模型长篇科学问答，减少幻觉，提升准确性。
SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA
- 通过文本与模拟器参数互译接口，实现从模拟器检索证据。
- 在气候、流行病学等领域的问答中，事实性提升16.3%，信息量提高30.4%。
- 针对可验证的细粒度命题进行动态校验，适合需要高可信度的科研场景。
大语言模型在生成长篇科学解释方面潜力巨大，但常出现幻觉，产生无支持或不一致的结论。检索增强生成（RAG）通过外部源增强可信度，而科学模拟器能验证定量假设并捕捉动态变化。然而，基于模拟的RAG面临两大挑战：如何从模拟器中检索，以及如何高效验证和更新长答案。为此，我们提出SimulRAG，一种通用检索接口可实现文本与模拟器参数/输出间的转换。该框架引入声明级生成与不确定性估计及模拟器边界评估（UE+SBA），选择性地验证和更新可被模拟器检验的原子声明。不同于先工具后生成或整体重写，它先生成多样化答案，再用模拟器证据接地不确定且可验证的声明。我们还发布了一个涵盖气候科学、流行病学和城市规划的长篇科学问答基准，其真实答案经模拟和人工标注双重验证。实验表明，SimulRAG相比最强的适配基线，信息量提升30.4%，事实性提升16.3%，且UE+SBA显著提高声明级效率与质量。
原文摘要 · Abstract (English)
Large Language Models (LLMs) show promise in generating long-form scientific explanations that synthesize evidence and connect multiple factors. However, in long-form scientific question answering, LLMs often hallucinate, producing unsupported or inconsistent claims. Retrieval-Augmented Generation (RAG) improves trustworthiness by grounding generation in external sources; scientific simulators are valuable because they can validate quantitative hypotheses and capture evolving dynamics. Yet simulation-based RAG is non-trivial due to two challenges: how to retrieve from scientific simulators, and how to efficiently verify and update long-form answers. To overcome these challenges, we propose SimulRAG, a simulator-based RAG framework with a generalized retrieval interface that translates between text and simulator parameters/outputs. SimulRAG further introduces claim-level generation with uncertainty estimation and simulator boundary assessment (UE+SBA) to selectively verify and update claims. Unlike tool-first or holistic answer revision, it first elicits diverse answers without retrieval and then grounds uncertain, simulator-verifiable atomic claims with simulator evidence. We also release a long-form scientific QA benchmark spanning climate science, epidemiology, and urban planning, with ground truth verified by simulations and human annotators. Experiments show SimulRAG improves informativeness by 30.4% and factuality by 16.3% over the strongest adapted RAG baselines, while UE+SBA enhances claim-level efficiency and quality.
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。