Model immunology: negative selection finds a one-sided adapter fingerprint
The base model is "self". The adapter is "non-self". Negative selection keeps only probes
that the self does not recognize but the non-self does. This is a cross-disciplinary
evaluation experiment, not a container.
Reproduce:
python research/immune_probes.py # -> research/results/immune_probes.json
Enter fullscreen mode
Exit fullscreen mode
Setup
Host: 4-bit Qwen3B.
Self: base model.
Non-self: SST-2 LoRA adapter.
400 SST-2 test rows; label-token logit scoring.
Base accuracy: 60.8% . Adapter accuracy: 94.5% .
Candidate detectors: rows where base is wrong and adapter is right.
The self is biased
There are 143 candidates . Every single one is a positive review.
The base over-predicts negative, so its errors are almost entirely positive rows that it
calls negative. The adapter's non-self behavior is not "sentiment in general"; it is
positive-sentiment rescue .…