REVIEW 4 cited by
Representation Surgery: Theory and Practice of Affine Steering
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Representation Surgery: Theory and Practice of Affine Steering
read the original abstract
Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. In the case of neural language models, an encoding of the undesirable behavior is often present in the model's representations. Thus, one natural (and common) approach to prevent the model from exhibiting undesirable behavior is to steer the model's representations in a manner that reduces the probability of it generating undesirable text. This paper investigates the formal and empirical properties of steering functions, i.e., transformation of the neural language model's representations that alter its behavior. First, we derive two optimal, in the least-squares sense, affine steering functions under different constraints. Our theory provides justification for existing approaches and offers a novel, improved steering approach. Second, we offer a series of experiments that demonstrate the empirical effectiveness of the methods in mitigating bias and reducing toxic generation.
Forward citations
Cited by 4 Pith papers
-
Conditional Optimal Bridge for Riemannian Activation Steering
Casting activation steering as a Schrödinger Bridge on the residual hypersphere derives the log-density-ratio objective and yields query-adaptive directions that beat fixed baselines without OOD collapse.
-
ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
ASRU combines activation redirection and reward-optimized fine-tuning to unlearn cross-modal sensitive knowledge in MLLMs, reporting +24.6% better unlearning effectiveness and 5.8x higher generation quality on Qwen3-V...
-
Conceptors for Semantic Steering
Conceptors as soft projection matrices from bipolar activations offer a multidimensional, compositional, and geometrically principled method for semantic steering in LLMs that outperforms single-vector baselines in mu...
-
Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment
Learning an input-conditioned mapping from embeddings to the best single steering layer (W2S) consistently beats fixed-layer CAA and L2S on 13 behaviors for two LLMs, in- and out-of-distribution.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.