Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Expert Selections In MoE Models Reveal (Almost) As Much As Text

Amir Nuriyev, Gabriel Kulp

Published

Feb 4, 2026

Citations

0

Trust level

Low

Usefulness score

0/100 (Low)

Extraction confidence

35% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Mar 13, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

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

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

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
Detected
Eval setup described
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

We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone. In MoE models, each token is routed to a subset of expert subnetworks; we show these routing decisions leak substantially more information than previously understood. Prior work using logistic regression achieves limited reconstruction; we show that a 3-layer MLP improves this to 63.1% top-1 accuracy, and that a transformer-based sequence decoder recovers 91.2% of tokens top-1 (94.8% top-10) on 32-token sequences from OpenWebText after training on 100M tokens. These results connect MoE routing to the broader literature on embedding inversion. We outline practical leakage scenarios (e.g., distributed inference and side channels) and show that adding noise reduces but does not eliminate reconstruction. Our findings suggest that expert selections in MoE deployments should be treated as sensitive as the underlying text.

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.

"We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone."

Quality Controls

missing

Not reported

No explicit QC controls found.

"We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone."

Reported Metrics

partial

Accuracy, Top 1 accuracy

Useful for evaluation criteria comparison.

"Prior work using logistic regression achieves limited reconstruction; we show that a 3-layer MLP improves this to 63.1% top-1 accuracy, and that a transformer-based sequence decoder recovers 91.2% of tokens top-1 (94.8% top-10) on 32-token sequences from OpenWebText after training on 100M tokens."

Rater Population

partial

Domain Experts

Helpful for staffing comparability.

"We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone."

Benchmarks and datasets

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

Reported metrics

accuracytop-1 accuracy
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Domain Experts
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone.

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

Key takeaways

  • We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone.
  • In MoE models, each token is routed to a subset of expert subnetworks; we show these routing decisions leak substantially more information than previously understood.
  • Prior work using logistic regression achieves limited reconstruction; we show that a 3-layer MLP improves this to 63.1% top-1 accuracy, and that a transformer-based sequence decoder recovers 91.2% of tokens top-1 (94.8% top-10) on 32-token sequences from OpenWebText after training on 100M tokens.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • 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

Expert verification evaluation Accuracy

Contribution summary

  • We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone.
  • In MoE models, each token is routed to a subset of expert subnetworks; we show these routing decisions leak substantially more information than previously understood.
  • Prior work using logistic regression achieves limited reconstruction; we show that a 3-layer MLP improves this to 63.1% top-1 accuracy, and that a transformer-based sequence decoder recovers 91.2% of tokens top-1 (94.8% top-10) on 32-token…

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

    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: accuracy, top-1 accuracy