Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Who Gets Unmasked? Sampler-Induced Bias in Diffusion Language Models

Xujun Che, Farsheed Haque, Depeng Xu, Xi Niu +1 more

Published

Oct 17, 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

Not reported

Signals refreshed

Oct 17, 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

Read the full paper before copying any benchmark, metric, or protocol choices.

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

Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it. We show that this second decision changes who appears in generated text, a sampler-induced bias on top of the model's own. Common commit rules, including LLaDA's default, commit the positions whose sampled tokens are most probable; this peeking favors majority options. To separate the sampler from the model, we read the model's belief about a fork, such as a protagonist's gender, in one forward pass, and show that this belief matches exact sampling from the model. Measured against it, peeking samplers on LLaDA and Dream amplify occupational gender stereotypes and collapse opinion distributions, and confidence-based ordering shifts gender-balanced occupations toward men, more so under faster parallel decoding. We propose Fork-First Sampling, which decides the fork before anything else is written: it follows the belief or any target distribution, improves fluency, and avoids the stories that remark on the protagonist's gender, which prompt-based fixes produce, at the cost of one forward pass. Fairness evaluations of dLLMs should report the commit rule.

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.

"Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it."

Benchmarks and datasets

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

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
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

Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it.

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

Key takeaways

  • Diffusion language models (dLLMs) generate by gradually unmasking a canvas, so their samplers decide not only which token to write but also when to commit it.
  • We show that this second decision changes who appears in generated text, a sampler-induced bias on top of the model's own.
  • Common commit rules, including LLaDA's default, commit the positions whose sampled tokens are most probable; this peeking favors majority options.

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

  • We show that this second decision changes who appears in generated text, a sampler-induced bias on top of the model's own.
  • We propose Fork-First Sampling, which decides the fork before anything else is written: it follows the belief or any target distribution, improves fluency, and avoids the stories that remark on the protagonist's gender, which prompt-based…
  • Fairness evaluations of dLLMs should report the commit rule.

Why it matters for eval

  • Fairness evaluations of dLLMs should report the commit rule.

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

    No metric terms extracted.