SALT: Salience-Aware Lexical Trie for Long-Context Compression

arXiv:2607.17486 · cs.PF, cs.AI, cs.LG · Submitted 2026-07-20 · Read on arXiv

cs.PF, cs.AI, cs.LG

Submitted: 2026-07-20

Updated: 2026-08-31

Code: https://github.com/oteomamo/SALT

Terminology

• Accuracy — 16× in this paper · explained in 1 episode
• KV cache — 8× in this paper · explained in 3 episodes
• Decode — 6× in this paper · explained in 2 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Model-Agnostic — 5× in this paper · explained in 2 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Pruning — 4× in this paper · explained in 4 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Core — 2× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 2× in this paper
• Sparse Attention — 2× in this paper · explained in 5 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Distillation — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
• The Llama 3 Herd of Models
• RULER: What's the Real Context Size of Your Long-Context Language Models?
• FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration
• Towards General Text Embeddings with Multi-stage Contrastive Learning
• Compressive Transformers for Long-Range Sequence Modelling
• C-Pack: Packed Resources For General Chinese Embeddings
• Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression

Related papers

• A Controlled Study of Memory Hierarchy Transitions in Quantum Circuit Simulation on Apple M4 Pro Unified Memory Architecture
• The Caf'e in Amsterdam: When the Incumbent Becomes the Oracle