GraphLit learns representations from ~20,000 dynamic heterogeneous character networks extracted from Project Gutenberg novels via masked graph autoencoders and outperforms text-only and graph-only baselines on 12 character-related tasks.
Longbench pro: A more realistic and comprehensive bilingual long- context evaluation benchmark
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
UNIQUE enables efficient top-k sparse attention in LLMs by using a mean-plus-std page importance score and a soft-mask training approach, achieving up to 11.4x kernel speedup while preserving performance.
citing papers explorer
-
GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study
GraphLit learns representations from ~20,000 dynamic heterogeneous character networks extracted from Project Gutenberg novels via masked graph autoencoders and outperforms text-only and graph-only baselines on 12 character-related tasks.
-
The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management
The Efficiency Frontier framework models LLM context management as a deployment-aware optimization problem balancing performance, token cost, and amortized preprocessing, with HotpotQA experiments showing 25% token reduction and over 50% cost savings for compression in high-performance regimes.
-
UNIQUE: Universal Top-k Sparse Attention for Training-free Inference and Sparsity-aware Training
UNIQUE enables efficient top-k sparse attention in LLMs by using a mean-plus-std page importance score and a soft-mask training approach, achieving up to 11.4x kernel speedup while preserving performance.