REVIEW 5 cited by
Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
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
read the original abstract
Representation engineering methods have recently shown promise for enabling efficient steering of model behavior. However, evaluation pipelines for these methods have primarily relied on subjective demonstrations, instead of quantitative, objective metrics. We aim to take a step towards addressing this issue by advocating for four properties missing from current evaluations: (i) contexts sufficiently similar to downstream tasks should be used for assessing intervention quality; (ii) model likelihoods should be accounted for; (iii) evaluations should allow for standardized comparisons across different target behaviors; and (iv) baseline comparisons should be offered. We introduce an evaluation pipeline grounded in these criteria, offering both a quantitative and visual analysis of how effectively a given method works. We use this pipeline to evaluate two representation engineering methods on how effectively they can steer behaviors such as truthfulness and corrigibility, finding that some interventions are less effective than previously reported.
Forward citations
Cited by 5 Pith papers
-
Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models
Persistent SAEs learn per-feature persistence coefficients from reconstruction, splitting features into fast local detectors and slow topic-tracking states that retain prompt-injection signals over long contexts.
-
Fine-Grained Interpretation of Political Opinions in Large Language Models
Four-dimensional political concept vectors learned from LLM internals can detect and partially steer political leanings better than a single left-right axis.
-
Transmuting prompts into weights
Instructions in prompts can be transmuted into reusable vector and matrix weight edits, so a language model follows them without seeing the text.
-
Understanding (Un)Reliability of Steering Vectors in Language Models
Steering vectors are unreliable when the target behavior does not correspond to a coherent, well-separated linear direction in activation space, and this coherence can be measured from training data.
-
Probabilistic Concept-Aware Steering for Trustworthy LLM Inference
PCS improves steering direction accuracy by adaptively sampling the intervention coefficient from a cosine-similarity-conditioned Gaussian, but its evaluation is partly circular because the optimal coefficient is chos...
Discussion (0). Continue with ORCID to comment.