研究人员推出UNREAL，一个将检索增强生成（RAG）和长上下文推理统一在单一模型中的新框架。该方法利用冻结的LLM内部表示，跨越从长提示到整个语料库的各种尺度选择证据。UNREAL仅添加了最少的训练参数，并在HotpotQA和2WikiMultiHopQA等基准测试中显著提高了召回率，同时还提高了长上下文任务的准确性并降低了计算成本。 AI
影响 为LLM中的证据选择建立了一种统一的方法，有可能提高检索和长上下文任务的效率和性能。
排序理由 该集群描述了一篇详细介绍新模型架构及其在各种基准测试中性能的新研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2610.08463v1 Announce Type: new Abstract: Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidenc…
Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidence across this range. We introduce UNifying REtri…
Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidence across this range. We introduce UNifying REtri…
Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidence across this range. We introduce UNifying REtri…