HFEPX · Eval paper review
Federico Marcuzzi, Martin Christoph, Iryna Gurevych, Alla Rozovskaya
Published
Oct 21, 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
Oct 22, 2026
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.
Useful as a secondary reference; validate protocol details against neighboring papers.
If you are doing eval pipeline work, start here
Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-native writers unrepresented. To address this gap, we investigate how grammatical errors by non-native writers affect social bias. We develop a controlled framework that injects common learner errors into prompts and apply it to three bias benchmarks covering stereotype alignment and demographic preference across gender, race, and religion. We find that grammatical errors increase bias, and the effect grows with the error rate. Among the four common error types we consider, preposition errors produce the largest and most consistent increase in stereotype alignment. Our analysis suggests that errors increase bias when they are more likely to interfere with comprehension. Finally, fine-tuning on erroneous texts reduces the bias increase caused by grammatical errors. Our findings show that bias evaluations based exclusively on well-formed prompts may underestimate the bias experienced by users whose English contains grammatical errors.
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.
Pairwise Preference
Directly usable for protocol triage.
"Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-native writers unrepresented."
Automatic Metrics
Includes extracted eval setup.
"Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-native writers unrepresented."
Not reported
No explicit QC controls found.
"Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-native writers unrepresented."
Not extracted
No benchmark anchors detected.
"Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-native writers unrepresented."
Error rate
Useful for evaluation criteria comparison.
"We find that grammatical errors increase bias, and the effect grows with the error rate."
No benchmark or dataset names were extracted from the available abstract.
Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-native writers unrepresented.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
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: error rate
