Eliciting Language Model Behaviors using Reverse Language Models

Despite advances in fine-tuning methods, language models (LMs) continue to output toxic and harmful responses on worst-case inputs, including adversarial attacks and jailbreaks. We train an LM on tokens in reverse order---a reverse LM---as a tool for identifying such worst-case inputs. By prompting a reverse LM with a problematic string, we can sample prefixes that are likely to precede the problematic suffix. We test our reverse LM by using it to guide beam search for prefixes that have high probability of generating toxic statements when input to a forwards LM. Our 160m parameter reverse LM outperforms the existing state-of-the-art adversarial attack method, GCG, when measuring the probability of toxic continuations from the Pythia-160m LM. We also find that the prefixes generated by our reverse LM for the Pythia model are more likely to transfer to other models, eliciting toxic responses also from Llama 2 when compared to GCG-generated attacks.

LEACE: Perfect linear concept erasure in closed form

Concept erasure aims to remove specified features from a neural representation. It can be used to improve fairness (e.g. preventing a model from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). In this paper, we introduce LEAst-squares Concept Erasure (LEACE), a fast closed-form method which provably prevents all linear classifiers from detecting a concept while inflicting the least possible damage to the representation. We apply LEACE to large language models with a novel procedure called “concept scrubbing,” which erases information about the target concept from every hidden layer in the network. We demonstrate the usefulness of our method on two tasks: measuring the extent to which language models rely on part-of-speech information, and reducing gender bias in BERT embeddings.

Eliciting Latent Predictions from Transformers with the Tuned Lens

We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer. To do so, we train an affine probe for each block in a frozen pretrained model, making it possible to decode every hidden state into a distribution over the vocabulary. Our method, the tuned lens, is a refinement of the earlier ``logit lens'' technique, which yielded useful insights but is often brittle.

We test our method on various autoregressive language models with up to 20B parameters, showing it to be more predictive, reliable and unbiased than the logit lens. With causal experiments, we show the tuned lens uses similar features to the model itself. We also find the trajectory of latent predictions can be used to detect malicious inputs with high accuracy. All code needed to reproduce our results can be found at here.