RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval
RecaLLM:通过显式上下文检索解决‘思维迷失’现象
机构 * University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)
AI总结 RecaLLM通过交替推理与显式上下文检索解决推理过程中因长上下文导致的检索性能下降问题,显著提升了RULER和HELMET基准测试表现。
Comments Code, data, and models available at https://github.com/kswhitecross/RecaLLM