HFEPX · Eval paper review
Uwe König, Hamza Kazmi, Ruizhe Li, Maheep Chaudhary
Published
Jun 9, 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
Jun 26, 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
Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning. While qualitative evidence supports the existence of this effect, its magnitude has not been systematically characterized. This study quantifies subliminal behavioral transfer ratios by steering two teacher models (Llama-2-7B-Chat and Qwen2.5-7B-Instruct) at varying steering strengths and distilling student models using only benign data. Evaluation on 100 JailbreakBench prompts with GPT-4.1, serving as the evaluator, indicates that transfer is robust but exhibits distinct scaling behaviors. Llama-2 demonstrates a sharp threshold ($τ= {0.25,0.32} \ \text{beyond} \ α= -0.15$), whereas Qwen2.5 displays continuous and higher levels of transfer ($τ$ up to $0.61$).
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.
Red Team
Directly usable for protocol triage.
"Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning."
None explicit
Validate eval design from full paper text.
"Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning."
Not reported
No explicit QC controls found.
"Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning."
Jailbreakbench
Useful for quick benchmark comparison.
"Evaluation on 100 JailbreakBench prompts with GPT-4.1, serving as the evaluator, indicates that transfer is robust but exhibits distinct scaling behaviors."
Not extracted
No metric anchors detected.
"Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning."
No metric terms were extracted from the available abstract.
Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
Detected: Red Team
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: Jailbreakbench
Metric reporting is present
No metric terms extracted.
