conftrace_

context length

48 papers

Explore in graph

Co-occurring keywords

large language model (13587) long context (121) rotary position embedding (32) long-context understanding (24) language model (4599) efficient computing (781) attention mechanism (4001) inference efficiency (248) retrieval-augmented generation (1592) computational efficiency (362)

Papers

Too Long, Didn’t Model: Decomposing LLM Long Context Understanding With Novels EACL 2026
Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length ACL 2026
BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation AAAI 2026
Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models EACL 2026
NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts EMNLP 2025
What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs ACL 2025
Lost in the Distance: Large Language Models Struggle to Capture Long-Distance Relational Knowledge NAACL 2025
LongSafety: Enhance Safety for Long-Context LLMs ACL 2025
When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models EMNLP 2025
Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts EMNLP 2025
FocusLLM: Precise Understanding of Long Context by Dynamic Condensing ACL 2025
Cost-Optimal Grouped-Query Attention for Long-Context Modeling EMNLP 2025
LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios NAACL 2025
MedOdyssey: A Medical Domain Benchmark for Long Context Evaluation Up to 200K Tokens NAACL 2025
In-Context Learning with Long-Context Models: An In-Depth Exploration NAACL 2025
UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation ACL 2025
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding ACL 2025
More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAG EMNLP 2025
PEPE: Long-context Extension for Large Language Models via Periodic Extrapolation Positional Encodings EMNLP 2025
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval EMNLP 2025
Balancing Context Length and Mixing Times for Reinforcement Learning at Scale NIPS 2024
Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models IJCAI 2024
CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending ACL 2024
You Only Cache Once: Decoder-Decoder Architectures for Language Models NIPS 2024
Resonance RoPE: Improving Context Length Generalization of Large Language Models ACL 2024