HFEPX · Eval paper review
Yeb Havinga
Published
Oct 29, 2026
Citations
0
Trust level
Moderate
Usefulness score
50/100 (Medium)
Extraction confidence
55% (Moderate)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Oct 29, 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.
Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.
Best use
Secondary protocol comparison source
Use if you need
Background context only.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
The abstract does not clearly describe the evaluation setup.
Useful as a secondary reference; validate protocol details against neighboring papers.
If you are doing eval pipeline work, start here
Decision models are language models built to route, classify and triage: they return option probabilities from one forward pass, and an application acts on the top answer. They are offered off the shelf, trained for the decision format rather than for fairness or any one application, and we found no bias measurement in their cards. We test TypeSafe's closed Jev and five open decision models on gender-swapped yes/no decisions about people (Tamkin et al., 2023), BBQ, StereoSet and the gender-bias studies of Fulgu and Capraro (2024). Five of the six give women significantly more favourable answers than men (+0.05 to +0.10 in log-odds), and a gender swap changes 1-3.5% of top answers (Jev's partly through its call-to-call variation). The makers' recommended confidence gate removes many biased commitments but raises the stereotyped share of those it keeps in ambiguous BBQ gender questions (granite-switch 0.76 to 0.85, pplx 0.81 to 1.00). Probes show gender preferences in the same models: all six rate violence for a greater good as more acceptable against a man than against a woman, and two default to "girl" when forced to guess a child's gender without a cue. Decision-level and probability-level measures differ, so audits should read a model as its application does.
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.
"Decision models are language models built to route, classify and triage: they return option probabilities from one forward pass, and an application acts on the top answer."
None explicit
Validate eval design from full paper text.
"Decision models are language models built to route, classify and triage: they return option probabilities from one forward pass, and an application acts on the top answer."
Not reported
No explicit QC controls found.
"Decision models are language models built to route, classify and triage: they return option probabilities from one forward pass, and an application acts on the top answer."
BBQ
Useful for quick benchmark comparison.
"We test TypeSafe's closed Jev and five open decision models on gender-swapped yes/no decisions about people (Tamkin et al., 2023), BBQ, StereoSet and the gender-bias studies of Fulgu and Capraro (2024)."
Not extracted
No metric anchors detected.
"Decision models are language models built to route, classify and triage: they return option probabilities from one forward pass, and an application acts on the top answer."
No metric terms were extracted from the available abstract.
Decision models are language models built to route, classify and triage: they return option probabilities from one forward pass, and an application acts on the top answer.
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
No clear evaluation mode extracted.
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
Detected: BBQ
Metric reporting is present
No metric terms extracted.
