Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?

We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment. This problem is comprised of arithmetic questions posed in natural language, with an arbitrary adversarial string inserted before the question is complete. Even in the simple setting of 1-digit addition problems, it is easy to find adversarial prompts that make all tested models (including PaLM2, GPT4, Claude2) misbehave, and even to steer models to a particular wrong answer. We additionally provide a simple algorithm for finding successful attacks by querying those same models, which we name "prompt inversion rejection sampling" (PIRS). We finally show that models can be partially hardened against these attacks via reinforcement learning and via agentic constitutional loops. However, we were not able to make a language model fully robust against adversarial arithmetic attacks.

Character-Aware Models Improve Visual Text Rendering

Current image generation models struggle to reliably produce well-formed visual text. In this paper, we investigate a key contributing factor: popular text-to-image models lack character-level input features, making it much harder to predict a word's visual makeup as a series of glyphs. To quantify the extent of this effect, we conduct a series of controlled experiments comparing character-aware vs. character-blind text encoders. In the text-only domain, we find that character-aware models provide large gains on a novel spelling task (WikiSpell). Transferring these learnings onto the visual domain, we train a suite of image generation models, and show that character-aware variants outperform their character-blind counterparts across a range of novel text rendering tasks (our DrawText benchmark). Our models set a much higher state-of-the-art on visual spelling, with 30+ point accuracy gains over competitors on rare words, despite training on far fewer examples.

Extremely Simple Activation Shaping for Out-of-Distribution Detection

The separation between training and deployment of machine learning models implies that not all scenarios encountered in deployment can be anticipated during training, and therefore relying solely on advancements in training has its limits. Out-of-distribution (OOD) detection is an important area that stress-tests a model's ability to handle unseen situations: Do models know when they don't know? Existing OOD detection methods either incur extra training steps, additional data or make nontrivial modifications to the trained network. In contrast, in this work, we propose an extremely simple, post-hoc, on-the-fly activation shaping method, ASH, where a large portion (e.g. 90%) of a sample's activation at a late layer is removed, and the rest (e.g. 10%) simplified or lightly adjusted. The shaping is applied at inference time, and does not require any statistics calculated from training data. Experiments show that such a simple treatment enhances in-distribution and out-of-distribution sample distinction so as to allow state-of-the-art OOD detection on ImageNet, and does not noticeably deteriorate the in-distribution accuracy. We release alongside the paper two calls for explanation and validation, believing the collective power to further validate and understand the discovery. Calls, video and code can be found at: https://andrijazz.github.io/ash

What does a platypus look like? Generating customized prompts for zero-shot image classification

Open vocabulary models are a promising new paradigm for image classification. Unlike traditional classification models, open vocabulary models classify among any arbitrary set of categories specified with natural language during inference. This natural language, called "prompts", typically consists of a set of hand-written templates (e.g., "a photo of a {}") which are completed with each of the category names. This work introduces a simple method to generate higher accuracy prompts, without using explicit knowledge of the image domain and with far fewer hand-constructed sentences. To achieve this, we combine open vocabulary models with large language models (LLMs) to create Customized Prompts via Language models (CuPL, pronounced "couple"). In particular, we leverage the knowledge contained in LLMs in order to generate many descriptive sentences that are customized for each object category. We find that this straightforward and general approach improves accuracy on a range of zero-shot image classification benchmarks, including over one percentage point gain on ImageNet. Finally, this method requires no additional training and remains completely zero-shot. Code is available at https://github.com/sarahpratt/CuPL.

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench currently consists of 204 tasks, contributed by 442 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

When less is more: Simplifying inputs aids neural network understanding

How do neural network image classifiers respond to simpler and simpler inputs? And what do such responses reveal about the learning process? To answer these questions, we need a clear measure of input simplicity (or inversely, complexity), an optimization objective that correlates with simplification, and a framework to incorporate such objective into training and inference. Lastly we need a variety of testbeds to experiment and evaluate the impact of such simplification on learning. In this work, we measure simplicity with the encoding bit size given by a pretrained generative model, and minimize the bit size to simplify inputs in training and inference. We investigate the effect of such simplification in several scenarios: conventional training, dataset condensation and post-hoc explanations. In all settings, inputs are simplified along with the original classification task, and we investigate the trade-off between input simplicity and task performance. For images with injected distractors, such simplification naturally removes superfluous information. For dataset condensation, we find that inputs can be simplified with almost no accuracy degradation. When used in post-hoc explanation, our learning-based simplification approach offers a valuable new tool to explore the basis of network decisions.

Natural Adversarial Objects

Although state-of-the-art object detection methods have shown compelling performance, models often are not robust to adversarial attacks and out-of-distribution data. We introduce a new dataset, Natural Adversarial Objects (NAO), to evaluate the robustness of object detection models. NAO contains 7,934 images and 9,943 objects that are unmodified and representative of real-world scenarios, but cause state-of-the-art detection models to misclassify with high confidence. The mean average precision (mAP) of EfficientDet-D7 drops 74.5% when evaluated on NAO compared to the standard MSCOCO validation set. Moreover, by comparing a variety of object detection architectures, we find that better performance on MSCOCO validation set does not necessarily translate to better performance on NAO, suggesting that robustness cannot be simply achieved by training a more accurate model. We further investigate why examples in NAO are difficult to detect and classify. Experiments of shuffling image patches reveal that models are overly sensitive to local texture. Additionally, using integrated gradients and background replacement, we find that the detection model is reliant on pixel information within the bounding box, and insensitive to the background context when predicting class labels. NAO can be downloaded at https://drive.google.com/drive/folders/15P8sOWoJku6SSEiHLEts86ORfytGezi8.