Introducing v0.5 of the AI Safety Benchmark from MLCommons

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models. We introduce a principled approach to specifying and constructing the benchmark, which for v0.5 covers only a single use case (an adult chatting to a general-purpose assistant in English), and a limited set of personas (i.e., typical users, malicious users, and vulnerable users). We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0.5 benchmark. We plan to release version 1.0 of the AI Safety Benchmark by the end of 2024. The v1.0 benchmark will provide meaningful insights into the safety of AI systems. However, the v0.5 benchmark should not be used to assess the safety of AI systems. We have sought to fully document the limitations, flaws, and challenges of v0.5. This release of v0.5 of the AI Safety Benchmark includes (1) a principled approach to specifying and constructing the benchmark, which comprises use cases, types of systems under test (SUTs), language and context, personas, tests, and test items; (2) a taxonomy of 13 hazard categories with definitions and subcategories; (3) tests for seven of the hazard categories, each comprising a unique set of test items, i.e., prompts. There are 43,090 test items in total, which we created with templates; (4) a grading system for AI systems against the benchmark; (5) an openly available platform, and downloadable tool, called ModelBench that can be used to evaluate the safety of AI systems on the benchmark; (6) an example evaluation report which benchmarks the performance of over a dozen openly available chat-tuned language models; (7) a test specification for the benchmark.

Finetuning Text-to-Image Diffusion Models for Fairness

The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a distorted worldview and limit opportunities for minority groups. In this work, we frame fairness as a distributional alignment problem. Our solution consists of two main technical contributions: (1) a distributional alignment loss that steers specific characteristics of the generated images towards a user-defined target distribution, and (2) biased direct finetuning of diffusion model's sampling process, which leverages a biased gradient to more effectively optimize losses defined on the generated images. Empirically, our method markedly reduces gender, racial, and their intersectional biases for occupational prompts. Gender bias is significantly reduced even when finetuning just five soft tokens. Crucially, our method supports diverse perspectives of fairness beyond absolute equality, which is demonstrated by controlling age to a $75\%$ young and $25\%$ old distribution while simultaneously debiasing gender and race. Finally, our method is scalable: it can debias multiple concepts at once by simply including these prompts in the finetuning data. We hope our work facilitates the social alignment of T2I generative AI. We will share code and various debiased diffusion model adaptors.

Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation

Emotion Recognition in Conversation (ERC) plays an important role in driving the development of human-machine interaction. Emotions can exist in multiple modalities, and multimodal ERC mainly faces two problems: (1) the noise problem in the cross-modal information fusion process, and (2) the prediction problem of less sample emotion labels that are semantically similar but different categories. To address these issues and fully utilize the features of each modality, we adopted the following strategies: first, deep emotion cues extraction was performed on modalities with strong representation ability, and feature filters were designed as multimodal prompt information for modalities with weak representation ability. Then, we designed a Multimodal Prompt Transformer (MPT) to perform cross-modal information fusion. MPT embeds multimodal fusion information into each attention layer of the Transformer, allowing prompt information to participate in encoding textual features and being fused with multi-level textual information to obtain better multimodal fusion features. Finally, we used the Hybrid Contrastive Learning (HCL) strategy to optimize the model's ability to handle labels with few samples. This strategy uses unsupervised contrastive learning to improve the representation ability of multimodal fusion and supervised contrastive learning to mine the information of labels with few samples. Experimental results show that our proposed model outperforms state-of-the-art models in ERC on two benchmark datasets.

Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities

There is increasing attention being given to how to regulate AI systems. As governing bodies grapple with what values to encapsulate into regulation, we consider the technical half of the question: To what extent can AI experts vet an AI system for adherence to regulatory requirements? We investigate this question through two public sector procurement checklists, identifying what we can do now, what we should be able to do with technical innovation in AI, and what requirements necessitate a more interdisciplinary approach.

Inverse Scaling: When Bigger Isn't Better

Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, we present evidence for the claim that LMs may show inverse scaling, or worse task performance with increased scale, e.g., due to flaws in the training objective and data. We present empirical evidence of inverse scaling on 11 datasets collected by running a public contest, the Inverse Scaling Prize, with a substantial prize pool. Through analysis of the datasets, along with other examples found in the literature, we identify four potential causes of inverse scaling: (i) preference to repeat memorized sequences over following in-context instructions, (ii) imitation of undesirable patterns in the training data, (iii) tasks containing an easy distractor task which LMs could focus on, rather than the harder real task, and (iv) correct but misleading few-shot demonstrations of the task. We release the winning datasets at https://inversescaling.com/data to allow for further investigation of inverse scaling. Our tasks have helped drive the discovery of U-shaped and inverted-U scaling trends, where an initial trend reverses, suggesting that scaling trends are less reliable at predicting the behavior of larger-scale models than previously understood. Overall, our results suggest that there are tasks for which increased model scale alone may not lead to progress, and that more careful thought needs to go into the data and objectives for training language models.

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.

Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering

Recent years have witnessed the great accuracy performance of graph-based Collaborative Filtering (CF) models for recommender systems. By taking the user-item interaction behavior as a graph, these graph-based CF models borrow the success of Graph Neural Networks (GNN), and iteratively perform neighborhood aggregation to propagate the collaborative signals. While conventional CF models are known for facing the challenges of the popularity bias that favors popular items, one may wonder "Whether the existing graph-based CF models alleviate or exacerbate popularity bias of recommender systems?" To answer this question, we first investigate the two-fold performances w.r.t. accuracy and novelty for existing graph-based CF methods. The empirical results show that symmetric neighborhood aggregation adopted by most existing graph-based CF models exacerbate the popularity bias and this phenomenon becomes more serious as the depth of graph propagation increases. Further, we theoretically analyze the cause of popularity bias for graph-based CF. Then, we propose a simple yet effective plugin, namely r-AdjNorm, to achieve an accuracy-novelty trade-off by controlling the normalization strength in the neighborhood aggregation process. Meanwhile, r-AdjNorm can be smoothly applied to the existing graph-based CF backbones without additional computation. Finally, experimental results on three benchmark datasets show that our proposed method can improve novelty without sacrificing accuracy under various graph-based CF backbones.

Benchmarking Generalization via In-Context Instructions on 1,600+ Language Tasks

How can we measure the generalization of models to a variety of unseen tasks when provided with their language instructions? To facilitate progress in this goal, we introduce Natural-Instructions v2, a collection of 1,600+ diverse language tasks and their expert written instructions. More importantly, the benchmark covers 70+ distinct task types, such as tagging, in-filling, and rewriting. This benchmark is collected with contributions of NLP practitioners in the community and through an iterative peer review process to ensure their quality. This benchmark enables large-scale evaluation of cross-task generalization of the models -- training on a subset of tasks and evaluating on the remaining unseen ones. For instance, we are able to rigorously quantify generalization as a function of various scaling parameters, such as the number of observed tasks, the number of instances, and model sizes. As a by-product of these experiments. we introduce Tk-Instruct, an encoder-decoder Transformer that is trained to follow a variety of in-context instructions (plain language task definitions or k-shot examples) which outperforms existing larger models on our benchmark. We hope this benchmark facilitates future progress toward more general-purpose language understanding models.

NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation

Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on. In this paper, we present NL-Augmenter, a new participatory Python-based natural language augmentation framework which supports the creation of both transformations (modifications to the data) and filters (data splits according to specific features). We describe the framework and an initial set of 117 transformations and 23 filters for a variety of natural language tasks. We demonstrate the efficacy of NL-Augmenter by using several of its transformations to analyze the robustness of popular natural language models. The infrastructure, datacards and robustness analysis results are available publicly on the NL-Augmenter repository (\url{https://github.com/GEM-benchmark/NL-Augmenter}).