Extracting Latent Steering Vectors from Pretrained Language Models
Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to steer the model to generate a target sentence is already encoded within the model. Accordingly, we explore a different approach altogether: extracting latent vectors directly from pretrained language model decoders without fine-tuning. Experiments show that there exist steering vectors, which, when added to the hidden states of the language model, generate a target sentence nearly perfectly (> 99 BLEU) for English sentences from a variety of domains. We show that vector arithmetic can be used for unsupervised sentiment transfer on the Yelp sentiment benchmark, with performance comparable to models tailored to this task. We find that distances between steering vectors reflect sentence similarity when evaluated on a textual similarity benchmark (STS-B), outperforming pooled hidden states of models. Finally, we present an analysis of the intrinsic properties of the steering vectors. Taken together, our results suggest that frozen LMs can be effectively controlled through their latent steering space.
Code (1)
Tasks
Language ModelingLanguage ModellingSentenceSentence SimilaritySTSSTS-BText GenerationSimilar Papers 제목 키워드 기반
Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations
Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural act…
Steering LLM Reasoning Through Bias-Only Adaptation
Recent work on reasoning-oriented language models, exemplified by o1-like systems, suggests that reinforcement-learning (RL) finetuning does not create new capabilities but instead strengthens reasoning patterns already …
GSM8KMathReinforcement Learning (RL)Towards Inference-time Category-wise Safety Steering for Large Language Models
While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile na…
Safety AlignmentUnderstanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations
Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples an…
SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors
Speech-aware large language models often generalize poorly to out-of-domain settings. We propose SALSA (Speech-Aware LLM Adaptation via Learned Steering Activations), a lightweight adaptation method that learns layer-wis…