In this paper, we explore the feasibility of leveraging large language models (LLMs) to automate or otherwise assist human raters with identifying harmful content including hate speech, harassment, violent extremism, and election misinformation. Using a dataset of 50,000 user comments, we demonstrate that LLMs can achieve 90 % accuracy when compared to human verdicts. We explore how to best leverage these capabilities, proposing five design patterns that integrate LLMs with human rating, such as pre-filtering non-violative content, detecting potential errors in human rating, or surfacing critical context to support human rating. We outline how to support all of these design patterns using a single, optimized prompt. Beyond these synthetic experiments, we share how piloting our proposed techniques in a real-world review queue yielded a 41.5% improvement in optimizing available human rater capacity, and a 9–11 % increase (absolute) in precision and recall for detecting violative content.

This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication tasks. We demonstrate that RETSim is significantly more robust and accurate than MinHash and neural text embeddings, achieving new state-of-the-art performance on dataset deduplication, adversarial text retrieval benchmarks, and spam clustering tasks. Additionally, we introduce the W4NT3D benchmark (Wiki-40B 4dversarial Near-T3xt Dataset), enabling the evaluation of models on typo-laden near-duplicate text retrieval in a multilingual setting. RETSim and the W4NT3D benchmark are released under the MIT License at https://github.com/google/unisim.

This paper describes RETVec, an efficient, resilient, and multilingual text vectorizer designed for neural-based text processing. RETVec combines a novel character encoding with an optional small embedding model to embed words into a 256-dimensional vector space. The RETVec embedding model is pre-trained using pair-wise metric learning to be robust against typos and character-level adversarial attacks. In this paper, we evaluate and compare RETVec to state-of-the-art vectorizers and word embeddings on popular model architectures and datasets. These comparisons demonstrate that RETVec leads to competitive, multilingual models that are significantly more resilient to typos and adversarial text attacks. RETVec is available under the Apache 2 license at https://github.com/google-research/retvec.

We present a framework for coupling musical robots with interfaces based on open-ended control architecture, allowing for new and expanded forms of expression. The MahaDeviBot allows for a single performer to simultaneously control up to 12 drums. The ESitar doubles both as a multi input control interface, and as a traditional sitar. Finally, the BricKTable represents a completely open-ended control interface possible of multi user interaction, and real-time control data feedback.