Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering

• URL: http://arxiv.org/abs/2410.16314v3
• Date: Mon, 13 Jan 2025 16:53:02 GMT
• Title: Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering
• Authors: Joris Postmus, Steven Abreu,
• Abstract summary: This paper explores activation engineering, where outputs of pre-trained LLMs are controlled by manipulating their activations at inference time. We introduce conceptors - mathematical constructs that represent sets of activation vectors as ellipsoidal regions. Our experiments demonstrate that conceptors outperform traditional methods across multiple steering tasks.
• Score: 0.0
• License:
• Abstract: Large language models have transformed AI, yet reliably controlling their outputs remains a challenge. This paper explores activation engineering, where outputs of pre-trained LLMs are controlled by manipulating their activations at inference time. Unlike traditional methods using a single steering vector, we introduce conceptors - mathematical constructs that represent sets of activation vectors as ellipsoidal regions. Conceptors act as soft projection matrices and offer more precise control over complex activation patterns. Our experiments demonstrate that conceptors outperform traditional methods across multiple steering tasks. We further use Boolean operations on conceptors for combined steering goals that empirically outperform additively combining steering vectors on a set of tasks. These results highlight conceptors as a promising tool for more effective steering of LLMs. Our code is available on github.com/jorispos/conceptorsteering.

Related papers

• Steering Large Language Models with Feature Guided Activation Additions [0.0]
  We introduce Feature Guided Activation Additions (FGAA), a novel activation steering method. By operating in the latent space of a Sparse Autoencoder (SAE), FGAA constructs precise steering vectors. evaluations on Gemma-2-2B and Gemma-2-9B models demonstrate that FGAA outperforms existing steering methods.
  arXiv  Detail & Related papers  (2025-01-17T02:55:23Z)
• Controlling Large Language Models Through Concept Activation Vectors [30.348768212571255]
  We propose Generation with Concept Activation Vector (GCAV), a lightweight model control framework. GCAV ensures accurate control without requiring resource-extensive fine-tuning. Our framework achieves state-of-the-art performance with granular control, allowing for fine-grained adjustments of both the steering layers and the steering magnitudes for individual samples.
  arXiv  Detail & Related papers  (2025-01-10T07:41:48Z)
• Analyzing Fine-tuning Representation Shift for Multimodal LLMs Steering alignment [53.90425382758605]
  We show how fine-tuning alters the internal structure of a model to specialize in new multimodal tasks. Our work sheds light on how multimodal representations evolve through fine-tuning and offers a new perspective for interpreting model adaptation in multimodal tasks.
  arXiv  Detail & Related papers  (2025-01-06T13:37:13Z)
• Improving Instruction-Following in Language Models through Activation Steering [58.876600545898675]
  We derive instruction-specific vector representations from language models and use them to steer models accordingly. We demonstrate how this method can enhance model adherence to constraints such as output format, length, and word inclusion. Our findings demonstrate that activation steering offers a practical and scalable approach for fine-grained control in language generation.
  arXiv  Detail & Related papers  (2024-10-15T08:38:20Z)
• Vector-ICL: In-context Learning with Continuous Vector Representations [75.96920867382859]
  Large language models (LLMs) have shown remarkable in-context learning capabilities on textual data. We explore whether these capabilities can be extended to continuous vectors from diverse domains, obtained from black-box pretrained encoders. In particular, we find that pretraining projectors with general language modeling objectives enables Vector-ICL.
  arXiv  Detail & Related papers  (2024-10-08T02:25:38Z)
• Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization [34.05163996072159]
  "steering vectors" are extracted from the activations of human preference data. This work proposes an innovative approach that could produce more effective steering vectors through bi-directional preference optimization. Our method is designed to allow steering vectors to directly influence the generation probability of contrastive human preference data pairs.
  arXiv  Detail & Related papers  (2024-05-28T05:10:40Z)
• Improving Activation Steering in Language Models with Mean-Centring [10.101141087916133]
  We find that taking the average of activations associated with a target dataset, and subtracting the mean of all training activations, results in effective steering vectors. We also apply mean-centring to extract function vectors, more effectively triggering the execution of a range of natural language tasks by a significant margin.
  arXiv  Detail & Related papers  (2023-12-06T18:27:07Z)
• LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving [87.1164964709168]
  This work employs Large Language Models (LLMs) as a decision-making component for complex autonomous driving scenarios. Extensive experiments demonstrate that our proposed method not only consistently surpasses baseline approaches in single-vehicle tasks, but also helps handle complex driving behaviors even multi-vehicle coordination.
  arXiv  Detail & Related papers  (2023-10-04T17:59:49Z)
• GEM: Group Enhanced Model for Learning Dynamical Control Systems [78.56159072162103]
  We build effective dynamical models that are amenable to sample-based learning. We show that learning the dynamics on a Lie algebra vector space is more effective than learning a direct state transition model. This work sheds light on a connection between learning of dynamics and Lie group properties, which opens doors for new research directions.
  arXiv  Detail & Related papers  (2021-04-07T01:08:18Z)
• Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives [89.34229413345541]
  We propose a conditioning scheme which avoids pitfalls by learning the controller and its conditioning in an end-to-end manner. Our model predicts complex action sequences based directly on a dynamic image representation of the robot motion. We report significant improvements in task success over representative MPC and IL baselines.
  arXiv  Detail & Related papers  (2020-03-19T15:04:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.