The authors learn a low-dimensional manifold, meaning a compact continuous space, whose coordinates specify interventions to a frozen language model's internal activations.
Low-dimensional language-model steering supports more systematic black-box search
BOReFT learns a continuous intervention space inside a frozen language model, then searches it with Bayesian optimization to generate high-scoring discrete candidates.
Big Tech
Dhruv Agarwal · Rico Angell · Kavitha Srinivas · Tahira Naseem · Horst Samulowitz · Willie Neiswanger · +1 more
University of Massachusetts Amherst · New York University · IBM Research · University of Southern California
Research Digest··2 min read
Thread:Hidden-State Steering
Agarwal et al.
Why this paper
From IBM Research and 3 others
In one line
BOReFT learns a low-dimensional intervention manifold in a frozen LLM for Bayesian optimization of discrete black-box functions.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§