Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding

Matan Rusanovsky, Yoav Miron, Roy Uziel, Omer Belhasin +3 more

Published

Aug 20, 2026

Citations

0

Trust level

Moderate

Usefulness score

65/100 (Medium)

Extraction confidence

70% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Aug 20, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics General Pairwise Preference

Should you rely on this paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

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

Main weakness

No major weakness surfaced.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
65/100
Moderate-confidence candidate

Useful as a secondary reference; validate protocol details against neighboring papers.

If you are doing eval pipeline work, start here

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

Abstract

Speculative decoding accelerates language-model inference by drafting future tokens that the target model verifies in parallel. A diffusion-style block head such as DFlash is an attractive drafter, predicting an entire block of future tokens in one forward pass. However, it is trained on per-position marginals rather than the joint block distribution, so the tokens it emits are individually plausible yet jointly incoherent. We introduce LiLiCorr, a Lightweight Likelihood-based model that Correlates the per-position marginal distributions a drafter already produces. It keeps the top-k tokens at each position as candidates and processes them jointly, producing for each an in and an out vector. A pair of adjacent candidates matches when the earlier one's out vector has high cosine similarity with the later one's in vector. These matches capture the block's joint structure without ever materializing the full joint distribution. One lightweight network pass produces all the vectors, and the pairwise scores are then computed in parallel as batched matrix operations, leaving only a cheap greedy walk sequential. We further co-train the drafter with LiLiCorr, so it learns to propose candidates that correlate into longer accepted sequences. Over the vanilla DFlash drafter, LiLiCorr raises acceptance length on every benchmark by 9 to 19%, while its scoring head accounts for about 2.8% of the per-block latency. Against DFlash and two concurrent methods that also restore coherence at draft time, LiLiCorr delivers the highest throughput in 70 of 72 settings: nine benchmarks at two target sizes under greedy and temperature-one decoding, and a throughput sweep over six concurrencies, two input lengths and three entropy tiers, with all systems equally optimized on a common serving stack. Extending LiLiCorr to inputs an order of magnitude longer than it was trained on preserves that lead.

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

strong

Pairwise Preference

Directly usable for protocol triage.

"Speculative decoding accelerates language-model inference by drafting future tokens that the target model verifies in parallel."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Speculative decoding accelerates language-model inference by drafting future tokens that the target model verifies in parallel."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Speculative decoding accelerates language-model inference by drafting future tokens that the target model verifies in parallel."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Speculative decoding accelerates language-model inference by drafting future tokens that the target model verifies in parallel."

Reported Metrics

strong

Coherence

Useful for evaluation criteria comparison.

"Against DFlash and two concurrent methods that also restore coherence at draft time, LiLiCorr delivers the highest throughput in 70 of 72 settings: nine benchmarks at two target sizes under greedy and temperature-one decoding, and a throughput sweep over six concurrencies, two input lengths and three entropy tiers, with all systems equally optimized on a common serving stack."

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

coherence
Human feedback details
Uses human feedback
Yes
Feedback types
Pairwise Preference
Rater population
Not reported
Unit of annotation
Pairwise
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Secondary protocol comparison source

Research brief

Metadata summary

Speculative decoding accelerates language-model inference by drafting future tokens that the target model verifies in parallel.

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

Key takeaways

  • Speculative decoding accelerates language-model inference by drafting future tokens that the target model verifies in parallel.
  • A diffusion-style block head such as DFlash is an attractive drafter, predicting an entire block of future tokens in one forward pass.
  • However, it is trained on per-position marginals rather than the joint block distribution, so the tokens it emits are individually plausible yet jointly incoherent.

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

Pairwise preference evaluation

Contribution summary

  • We introduce LiLiCorr, a Lightweight Likelihood-based model that Correlates the per-position marginal distributions a drafter already produces.
  • Over the vanilla DFlash drafter, LiLiCorr raises acceptance length on every benchmark by 9 to 19%, while its scoring head accounts for about 2.8% of the per-block latency.
  • Against DFlash and two concurrent methods that also restore coherence at draft time, LiLiCorr delivers the highest throughput in 70 of 72 settings: nine benchmarks at two target sizes under greedy and temperature-one decoding, and a…

Why it matters for eval

  • Over the vanilla DFlash drafter, LiLiCorr raises acceptance length on every benchmark by 9 to 19%, while its scoring head accounts for about 2.8% of the per-block latency.
  • Against DFlash and two concurrent methods that also restore coherence at draft time, LiLiCorr delivers the highest throughput in 70 of 72 settings: nine benchmarks at two target sizes under greedy and temperature-one decoding, and a…

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Pairwise Preference

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    Detected: coherence