Pith. sign in

REVIEW 5 cited by

Representation Surgery: Theory and Practice of Affine Steering

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2402.09631 v7 pith:EVSXM3KO submitted 2024-02-15 cs.LG cs.CLcs.CY

Shashwat Singh , Shauli Ravfogel , Jonathan Herzig , Roee Aharoni , Ryan Cotterell , Ponnurangam Kumaraguru This is my paper
classification cs.LGcs.CLcs.CY
keywords behaviormodelsteeringundesirablelanguagerepresentationsaffineapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Conditional Optimal Bridge for Riemannian Activation Steering

    cs.LG 2026-07 accept novelty 7.0 of 10

    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.

  2. Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment

    cs.LG 2026-04 accept novelty 6.0 of 10

    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.

  3. Steering Protein Language Models

    q-bio.BM 2025-07 reject novelty 6.0 of 10

    Activation steering can guide protein language models to generate and optimize sequences with higher predicted thermostability, solubility, or GFP brightness, but only in surrogate-based evaluation.

  4. Abstract Counterfactuals for Language Model Agents

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Counterfactuals for LM agents computed over a high-level abstraction of the action, instead of its tokens, preserve the observed action's meaning across counterfactual contexts far more often than token-level counterfactuals.

  5. Improved Representation Steering for Language Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    RePS, a reference-free bidirectional preference optimization objective, improves representation steering and suppression for Gemma models, outperforming language-modeling objectives and approaching prompting performance.

Pith tools