Representation Tuning

• URL: http://arxiv.org/abs/2409.06927v4
• Date: Sun, 24 Nov 2024 06:31:59 GMT
• Title: Representation Tuning
• Authors: Christopher M. Ackerman,
• Abstract summary: Activation engineering is becoming increasingly popular as a means of online control of large language models. In this work, we extend the idea of inference-time steering with vectors that represent a behavioral direction of interest to tuning those vectors directly into the model.
• Score: 0.0
• License:
• Abstract: Activation engineering is becoming increasingly popular as a means of online control of large language models (LLMs). In this work, we extend the idea of inference-time steering with vectors that represent a behavioral direction of interest to tuning those vectors directly into the model, obviating the need for online control. First, we identify activation vectors related to honesty in an open-source LLM (Llama-2-13b-chat). Next, we demonstrate that model output can be made more or less honest by adding positive or negative multiples of these vectors to residual stream activations during generation. Then, we show that a similar effect can be achieved by fine-tuning the vectors directly into the model, by use of a dual loss function based on the cosine similarity of residual stream activations to the vectors combined with a standard token-based loss ("representation tuning"). Finally, we compare the generations in response to honesty-probing prompts from the resulting models to those from models fine-tuned with a token-based loss alone, and to those from the untuned model subjected to online steering. Overall, fine-tuning the vectors into the models using the cosine similarity plus token loss showed a stronger effect than online steering, and generalized better than using the standard loss, suggesting the potential utility of this approach as a safety measure. Code and data are available at https://github.com/cma1114/representation_tuning. Tuned models are available at https://huggingface.co/collections/cackerman/representation-tuning-66da1e5ab41cd1b824687d9f.

Related papers

• Activation Scaling for Steering and Interpreting Language Models [55.59689963561315]
  We argue that successfully intervening on a model is a prerequisite for interpreting its internal workings. We establish a three-term objective: a successful intervention should flip the correct with the wrong token and vice versa. Using gradient-based optimization, this objective lets us learn (and later evaluate) a specific kind of efficient and interpretable intervention.
  arXiv  Detail & Related papers  (2024-10-07T12:01:32Z)
• Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines [74.42485647685272]
  We focus on Generative Masked Language Models (GMLMs) We train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model. We adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality.
  arXiv  Detail & Related papers  (2024-07-22T18:00:00Z)
• Steering Without Side Effects: Improving Post-Deployment Control of Language Models [61.99293520621248]
  Language models (LMs) have been shown to behave unexpectedly post-deployment. We present KL-then-steer (KTS), a technique that decreases the side effects of steering while retaining its benefits. Our best method prevents 44% of jailbreak attacks compared to the original Llama-2-chat-7B model.
  arXiv  Detail & Related papers  (2024-06-21T01:37:39Z)
• Autoregressive Image Generation without Vector Quantization [31.798754606008067]
  Conventional wisdom holds that autoregressive models for image generation are typically accompanied by vector-quantized tokens. We propose to model the per-token probability distribution using a diffusion procedure, which allows us to apply autoregressive models in a continuous-valued space.
  arXiv  Detail & Related papers  (2024-06-17T17:59:58Z)
• Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals [14.741951369068877]
  We find that ubiquitous time series (TS) forecasting models are prone to severe overfitting. We introduce a dual-stream and subtraction mechanism, which is a deep Boosting ensemble learning method. The proposed method outperform existing state-of-the-art methods, yielding an average performance improvement of 11.9% across various datasets.
  arXiv  Detail & Related papers  (2024-02-04T03:54:31Z)
• Meaning Representations from Trajectories in Autoregressive Models [106.63181745054571]
  We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. We empirically show that the representations obtained from large models align well with human annotations, outperform other zero-shot and prompt-free methods on semantic similarity tasks, and can be used to solve more complex entailment and containment tasks that standard embeddings cannot handle.
  arXiv  Detail & Related papers  (2023-10-23T04:35:58Z)
• Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost [53.746169882193456]
  Recent works have proposed various sparse attention modules to overcome the quadratic cost of self-attention. We propose a model that resolves both problems by endowing each attention head with a mixed-membership Block Model. Our model outperforms previous efficient variants as well as the original Transformer with full attention.
  arXiv  Detail & Related papers  (2022-10-27T15:30:52Z)
• Extracting Latent Steering Vectors from Pretrained Language Models [14.77762401765532]
  We show that latent vectors can be extracted directly from 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. We find that distances between steering vectors reflect sentence similarity when evaluated on a textual similarity benchmark.
  arXiv  Detail & Related papers  (2022-05-10T19:04:37Z)
• Autoencoding Variational Autoencoder [56.05008520271406]
  We study the implications of this behaviour on the learned representations and also the consequences of fixing it by introducing a notion of self consistency. We show that encoders trained with our self-consistency approach lead to representations that are robust (insensitive) to perturbations in the input introduced by adversarial attacks.
  arXiv  Detail & Related papers  (2020-12-07T14:16:14Z)
• S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation [31.38329747789168]
  We propose a sequential variational autoencoder to learn disentangled representations of sequential data under self-supervision. We exploit the benefits of some readily accessible supervisory signals from input data itself or some off-the-shelf functional models. Our model can easily disentangle the representation of an input sequence into static factors and dynamic factors.
  arXiv  Detail & Related papers  (2020-05-23T00:44:38Z)

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.