RASER: 可恢复性感知的选择性升级路由器用于多跳问答
RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering
AI总结：
提出RASER路由器，基于单次RAG的六个特征决定是否升级到更昂贵的检索策略，在不增加额外LLM调用的情况下，在F1分数与SOTA相当的同时节省大量token。
摘要：
多跳问答系统通常对每个问题使用昂贵的检索。它们可能会分解问题、运行多轮检索或通过桥接实体搜索后再回答。所有这些策略都依赖于重复的LLM调用来重写或分解问题，这增加了额外的token成本，并且在LLM预算紧张时不适用。然而，我们的分析表明，许多多跳问题已经被单次RAG正确回答，因此对每个问题都进行额外检索浪费了预算。我们引入了RASER（可恢复性感知的选择性升级路由器），这是一系列基于单次RAG及其六个特征的廉价路由器。RASER-2决定是停止还是升级到额外检索动作PRUNE。RASER-3在单次RAG、PRUNE和迭代检索IRCoT之间进行选择，使用相同的特征但增加了显式的成本-准确率权衡。两个路由器都不需要额外的LLM调用来做决定。在六个LLM和三个多跳QA基准测试中，两个路由器在F1分数上与最先进的基线保持竞争力，同时仅消耗始终PRUNE的41-49%的token，并且也少于迭代和分解检索基线。
英文摘要：
Multi-hop question-answering systems often use expensive retrieval on every question. They may decompose the question, run several retrieval rounds, or search through bridge entities before answering. All of these strategies rely on repeated LLM calls to rewrite or decompose the question, which increases extra token cost, and it is not fitting when the LLM budget is tight. However, our analysis shows that lots of multi-hop questions are already answered correctly by a single one-shot RAG, so running an extra retrieval on every question wastes the budget. We introduce RASER (Recoverability-Aware Selective Escalation Router), a family of cheap routers built on one-shot RAG and six features from it. RASER-2 decides whether to stop or escalate to the extra-retrieval action PRUNE. RASER-3 chooses among one-shot RAG, PRUNE, and iterative retrieval IRCoT, using the same features but adding an explicit cost-accuracy trade-off. Neither router makes an extra LLM call to decide. Across six LLMs and three multi-hop QA benchmarks, both routers stay competitive with the other state-of-the-art (SOTA) baselines in F1 while spending only 41-49% of always-prune's tokens and also less than the iterative and decomposition retrieval 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。
