Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding

Junsung Hwang

Published

Jul 27, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

30% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Sep 29, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

Background context only.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
0/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read at every decode step. We find that attention keys are approximately low-rank within pages. A single low-rank projection shared across pages can miss page-specific directions; fitting a basis to each page better identifies the pages receiving the most attention at comparable stored selector cost. LOCKS stores a rank-$r$ spectral summary per page, reconstructs its within-page logits, and selects pages by log-sum-exp mass without reading candidate keys or values. It stays within about a point of FullKV on LongBench-v1, tracks the read-every-key exact-LSE oracle on RULER down to the smallest budgets, and retains quality furthest under tight budgets on AIME26 and MATH-500. At a $2048$-token budget it matches FullKV aggregate quality beyond $100$K context while attending about $2\%$ of tokens. Across ranks $2$-$8$, summaries use $4$-$10\%$ of full-KV bytes. On GH200 with GPU-resident KV, LOCKS reduces complete decode-step time by $1.8\times$ at $512$K context. With full KV offloaded to Grace memory, it reaches $3.82$-$4.22\times$ the faster dense backend's aggregate throughput at $64$K-$256$K by serving larger batches.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read at every decode step."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read at every decode step."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read at every decode step."

Benchmarks / Datasets

partial

LongBench, MATH 500

Useful for quick benchmark comparison.

"It stays within about a point of FullKV on LongBench-v1, tracks the read-every-key exact-LSE oracle on RULER down to the smallest budgets, and retains quality furthest under tight budgets on AIME26 and MATH-500."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read at every decode step."

Benchmarks and datasets

LongBenchMATH-500

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Math
Evaluation details
Evaluation modes
None
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read at every decode step.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read at every decode step.
  • We find that attention keys are approximately low-rank within pages.
  • A single low-rank projection shared across pages can miss page-specific directions; fitting a basis to each page better identifies the pages receiving the most attention at comparable stored selector cost.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read at every decode step.
  • We find that attention keys are approximately low-rank within pages.
  • A single low-rank projection shared across pages can miss page-specific directions; fitting a basis to each page better identifies the pages receiving the most attention at comparable stored selector cost.

Why it matters for eval

  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: LongBench, MATH-500

  • Metric reporting is present

    No metric terms extracted.