Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2607.17486

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

Oteo Mamo·Hyunjin Yi·Joydhriti Choudhury·Shangqian Gao·Weikuan Yu
View original source ↗Read source document ↗Export metadata ↓

Abstract

As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems. Existing input-level prompt compression methods address this, but rank each sentence by a scalar relevance score, treating the document as an unstructured pool of words and sentences. Under tight budgets, this causes theme collapse, where the dominant theme(s) of a document consumes the budget, discarding less-frequent yet task-relevant themes. Preserving thematic coverage instead requires allocating the budget across recurring themes rather than scoring sentences in isolation. To this end, we propose SALT, a model-agnostic extractive framework that organizes per-sentence keywords into a trie ordered by sentence frequency (SF), a lightweight, reusable proxy for document thematic structure. This trie-based organization smooths memory allocation and prevents dominant themes from monopolizing the budget. Multi-anchor retrieval activates trie nodes labeled by query keywords at any depth, and the trie persists across dialogue turns, supporting multi-turn use without re-encoding the document. By preserving document themes, SALT reduces the prefill computation and memory cost of long-context prompts while remaining composable with KV-cache methods that target decoding-time latency and memory.

Explore related subjects

cs.PFcs.AIcs.LG

Keep this discovery

BibTeXRIS

Oteo Mamo, Hyunjin Yi, Joydhriti Choudhury, Shangqian Gao, Weikuan Yu. 2026-08-31. SALT: Salience-Aware Lexical Trie for Long-Context Compression. https://arxiv.org/abs/2607.17486

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

cs.AI subjectcs.LG subjectcs.PF subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related discoveries

arXiv2026

Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning

Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications. Looped transformers address this by performing multiple latent iterations to refine each token beyond a single forward pass. However, we identify a latent overthinking phenomenon: most token predictions are already correct after the first pass, but are sometimes revised into errors in later iterations. We ask whether selectively skipping latent iterations can improve accuracy, and reveal significant potential with an oracle iteration policy that boosts performance by up to 7.3%. Motivated by this, we propose Think-at-Hard (TaH), a looped transformer optimized for selective iteration. TaH employs a lightweight neural decider to trigger latent iteration, only at tokens likely to be incorrect after the standard forward pass. During latent iterations, depth-aware Low-Rank Adaptation (LoRA) modules shift the objective from general next-token prediction to focused hard-token refinement. A duo-causal attention mechanism extends attention from the token sequence dimension to an additional iteration depth dimension, enabling cross-iteration information flow with full sequential parallelism. Experiments on nine benchmarks show consistent gains across math, QA, and coding tasks. With identical parameter counts, TaH outperforms always-iterate baselines by 3.8-4.4% while skipping iterations on 93% of tokens, and exceeds single-iteration Qwen3 baselines by 3.0-3.8%. When allowing <3% more parameters from LoRA and decider, the gains further increase to 5.3-6.2% and 6.1-6.8%, respectively. Our code is available at https://github.com/thu-nics/TaH.

cs.CL↗
arXiv2026

Spectral Analysis for Sparse Matrix Computation: Insights and Potential

Sparse computations are fundamental to scientific computing, graph analytics, and machine learning, yet their performance is highly sensitive to the diverse sparsity and patterns. This is because cache reuse, memory coalescing, and load balancing depend critically on the sparsity patterns. This work gives the first known exploration of the connections between sparse matrix computation and spectral analysis by treating sparse matrices as two-dimensional signals and analyzing their frequency-domain representations through Fast Fourier Transform. We show that spectral signatures uncover global structural characteristics that are not sufficiently captured by conventional spatial statistics and provide complementary information for understanding sparse computation performance. Experiments on incorporating spectral features into machine-learning-based SpMV format selection demonstrate the usefulness of such spectral analysis over a state-of-the-art spatial-only model. By uncovering the principled connections between spectral characteristics and sparse matrix computations, this work introduces a novel analytical perspective into sparse computation, and provides a new approach to enhancing the current sparse structure characterization and optimization. On pruned LLM decoding, adding spectral features improves kernel selection and yields 1.035--1.245$\times$ kernel speedups.

cs.PF↗
arXiv2026

Characterization of Request and Token Energy Costs for LLM Inference Workloads on GPU Platforms

Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes token-normalized metrics incomplete, since average output-token energy can decrease even when total request energy increases. We characterize this behavior with a decomposed energy model: a fixed one-time prefill with a fixed generation setup cost, while each output-token generation step adds marginal step energy. We evaluate this LLM inference energy model on NVIDIA H100 and H200 GPUs across dense and mixture-of-experts (MoE) models, reporting both request energy and token energy as functions of model type (M), phase (P), batch size (B), context length (C), and output length (N). For Llama-3.2-1B on H200 at batch-16 and context-4K, increasing output length from 10 to 512 tokens reduces token energy from 7.46 to 0.72 J/token while total batched inference-window energy increases from 1.19 to 5.93 kJ. Batching also reduces token energy, but the gain is context-bounded: at 10 output tokens, the batch-16 to batch-1 gain falls from 6.31x at context-512 to 1.17x at context-4K. MoE models amplify this effect: sparse routing and fragmented expert execution increase fixed energy at low concurrency, while batching spreads that energy across more generated tokens and substantially narrows the dense-vs.-MoE token-energy gap. These results show that energy-aware serving should jointly optimize both request energy and token energy, rather than only reducing per-token energy cost.

cs.PF↗