Tag
A Meta 与密歇根州立大学的新论文发现,LLM 构建的推理图质量差异很大,其错误会传导到基于这些图计算出的答案和置信度中;研究测试了 9 个模型,指出图的质量更多取决于模型家族与图结构而非规模。
This paper introduces D2F-ReAG, a novel paradigm for multi-hop reasoning-augmented generation that dynamically controls reasoning depth by judging root-level reasoning reliability and decomposing questions into sub-questions when needed, improving accuracy on multi-hop benchmarks.
Proposes Decompose-and-Refine (DaR), a framework for statute-grounded legal question answering that decomposes complex questions into atomic sub-questions and generates parametric queries for precise statutory retrieval, showing improvements on the KoBLEX benchmark.
MemReread introduces a method for long-context reasoning that avoids intermediate retrieval by decomposing questions and rereading text to recover discarded information, achieving linear time complexity. It outperforms baseline frameworks on long-context reasoning tasks.