LongBench
Emerging6papers using it
2024first seen
LongBench is a comprehensive benchmark for multilingual and multi-task purposes, with the goal to fully measure and evaluate the ability of pre-trained language models to understand long text. This dataset consists of twenty different tasks, covering key long-text application scenarios such as multi-document QA, single
Papers using LongBench (6)
- LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction SynthesisDepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache CompressionVarRate: Training-Free Variable-Rate KV Cache Compression for Long-Context LLMsGRASP: Graph Agentic Search over Propositions for Multi-hop Question AnsweringLearning to Evict from Key-Value CacheLightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation