Menu

Model immunology: negative selection finds a one-sided adapter fingerprint
📰

Model immunology: negative selection finds a one-sided adapter fingerprint

DEV Community: machinelearning·mycute·7 days ago
#2naoT6FK
Reading 0:00
15s threshold

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 .…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.