HFEPX · Eval paper review
Ilija Subasic, Brett Levert, Andrew Rabinovich, Sajjad Pakdamansavoji +1 more
Published
Oct 27, 2026
Citations
0
Trust level
Moderate
Usefulness score
77/100 (High)
Extraction confidence
70% (Moderate)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Oct 27, 2026
This paper has strong direct human-feedback and evaluation protocol signal and is suitable as a primary eval pipeline reference.
Use this for comparison and orientation, not as your only source.
Best use
Primary benchmark and eval reference
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.
Use this as a primary source when designing or comparing eval protocols.
If you are doing eval pipeline work, start here
LLM-as-a-Judge has become a standard for evaluating large language models, yet most approaches implicitly assume that a single judge prompt functions as a stable evaluation instrument. Prior work has primarily explored deliberate prompt modifications such as scoring rubrics, role descriptions, or chain-of-thought reasoning in order to optimize accuracy. In contrast, we investigate whether validated prompt variants intended to preserve evaluation semantics while differing in surface realization (\textit{paraphrastic rephrasings}) yield consistent judgments under a fixed evaluation task. We introduce \textit{Prompt Lottery}, a phenomenon in which paraphrastic rephrasings produce different LLMaJ judgments. Across a large-scale study spanning diverse evaluation tasks, judge families, and model backbones, we find that these variations can alter evaluation outcomes and, in some settings, reverse relative model rankings. A user study with 10 human annotators shows that LLMaJ judges exhibit 6-9$\times$ larger agreement degradation under prompt rephrasings than humans, falling below the generally accepted threshold in usability studies. This indicates that single-prompt evaluation is insufficiently robust for model ranking. Finally, we show that multi-prompt aggregation substantially improves robustness by emphasizing judgments that remain consistent across prompt variants.
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.
Rubric Rating
Directly usable for protocol triage.
"LLM-as-a-Judge has become a standard for evaluating large language models, yet most approaches implicitly assume that a single judge prompt functions as a stable evaluation instrument."
Llm As Judge, Automatic Metrics
Includes extracted eval setup.
"LLM-as-a-Judge has become a standard for evaluating large language models, yet most approaches implicitly assume that a single judge prompt functions as a stable evaluation instrument."
Not reported
No explicit QC controls found.
"LLM-as-a-Judge has become a standard for evaluating large language models, yet most approaches implicitly assume that a single judge prompt functions as a stable evaluation instrument."
Not extracted
No benchmark anchors detected.
"LLM-as-a-Judge has become a standard for evaluating large language models, yet most approaches implicitly assume that a single judge prompt functions as a stable evaluation instrument."
Accuracy, Agreement
Useful for evaluation criteria comparison.
"Prior work has primarily explored deliberate prompt modifications such as scoring rubrics, role descriptions, or chain-of-thought reasoning in order to optimize accuracy."
No benchmark or dataset names were extracted from the available abstract.
LLM-as-a-Judge has become a standard for evaluating large language models, yet most approaches implicitly assume that a single judge prompt functions as a stable evaluation instrument.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
Detected: Rubric Rating
Evaluation mode is explicit
Detected: Llm As Judge, 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, agreement
