RULER

This is a synthetic dataset generated using 📏 RULER: What’s the Real Context Size of Your Long-Context Language Models?. It can be used to evaluate long-context language models with configurable sequence length and task complexity. Currently, It includes 4 tasks from RULER: QA2 (hotpotqa after adding distracting infor

Papers using RULER (18)

IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference2026RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval2026ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference2026LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding2026LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning2026FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning2026Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs2026Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs2026Towards robust long-context understanding of large language model via active recap learning2026MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training2025LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions2025Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation2025Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation2025CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective2025Does RAG Really Perform Bad For Long-Context Processing?2025NExtLong: Toward Effective Long-Context Training without Long Documents2025Why Does the Effective Context Length of LLMs Fall Short?2024 · 1 citesBreaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models2024