SpecRaGE: Robust and Generalizable Multi-view Spectral Representation Learning

Multi-view representation learning (MvRL) has garnered substantial attention in recent years, driven by the increasing demand for applications that can effectively process and analyze data from multiple sources. In this context, graph Laplacian-based MvRL methods have demonstrated remarkable success in representing multi-view data. However, these methods often struggle with generalization to new data and face challenges with scalability. Moreover, in many practical scenarios, multi-view data is contaminated by noise or outliers. In such cases, modern deep-learning-based MvRL approaches that rely on alignment or contrastive objectives can lead to misleading results, as they may impose incorrect consistency between clear and corrupted data sources. We introduce $\textit{SpecRaGE}$, a novel fusion-based framework that integrates the strengths of graph Laplacian methods with the power of deep learning to overcome these challenges. SpecRage uses neural networks to learn parametric mapping that approximates a joint diagonalization of graph Laplacians. This solution bypasses the need for alignment while enabling generalizable and scalable learning of informative and meaningful representations. Moreover, it incorporates a meta-learning fusion module that dynamically adapts to data quality, ensuring robustness against outliers and noisy views. Our extensive experiments demonstrate that SpecRaGE outperforms state-of-the-art methods, particularly in scenarios with data contamination, paving the way for more reliable and efficient multi-view learning. Our code will be made publicly available upon acceptance.

G-SPARC: SPectral ARchitectures tackling the Cold-start problem in Graph learning

Graphs play a central role in modeling complex relationships across various domains. Most graph learning methods rely heavily on neighborhood information, raising the question of how to handle cold-start nodes - nodes with no known connections within the graph. These models often overlook the cold-start nodes, making them ineffective for real-world scenarios. To tackle this, we propose G-SPARC, a novel framework addressing cold-start nodes, that leverages generalizable spectral embedding. This framework enables extension to state-of-the-art methods making them suitable for practical applications. By utilizing a key idea of transitioning from graph representation to spectral representation, our approach is generalizable to cold-start nodes, capturing the global structure of the graph without relying on adjacency data. Experimental results demonstrate that our method outperforms existing models on cold-start nodes across various tasks like node classification, node clustering, and link prediction. G-SPARC provides a breakthrough built-in solution to the cold-start problem in graph learning. Our code will be publicly available upon acceptance.

CoverBench: A Challenging Benchmark for Complex Claim Verification

There is a growing line of research on verifying the correctness of language models' outputs. At the same time, LMs are being used to tackle complex queries that require reasoning. We introduce CoverBench, a challenging benchmark focused on verifying LM outputs in complex reasoning settings. Datasets that can be used for this purpose are often designed for other complex reasoning tasks (e.g., QA) targeting specific use-cases (e.g., financial tables), requiring transformations, negative sampling and selection of hard examples to collect such a benchmark. CoverBench provides a diversified evaluation for complex claim verification in a variety of domains, types of reasoning, relatively long inputs, and a variety of standardizations, such as multiple representations for tables where available, and a consistent schema. We manually vet the data for quality to ensure low levels of label noise. Finally, we report a variety of competitive baseline results to show CoverBench is challenging and has very significant headroom. The data is available at https://huggingface.co/datasets/google/coverbench .

Sparse Binarization for Fast Keyword Spotting

With the increasing prevalence of voice-activated devices and applications, keyword spotting (KWS) models enable users to interact with technology hands-free, enhancing convenience and accessibility in various contexts. Deploying KWS models on edge devices, such as smartphones and embedded systems, offers significant benefits for real-time applications, privacy, and bandwidth efficiency. However, these devices often possess limited computational power and memory. This necessitates optimizing neural network models for efficiency without significantly compromising their accuracy. To address these challenges, we propose a novel keyword-spotting model based on sparse input representation followed by a linear classifier. The model is four times faster than the previous state-of-the-art edge device-compatible model with better accuracy. We show that our method is also more robust in noisy environments while being fast. Our code is available at: https://github.com/jsvir/sparknet.

Multilingual Instruction Tuning With Just a Pinch of Multilinguality

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. One promising approach is cross-lingual transfer, where a model acquires specific functionality on some language by finetuning on another language. In this work, we investigate how multilinguality during instruction tuning of a multilingual LLM affects instruction-following across languages. We first show that many languages transfer some instruction-following capabilities to other languages from even monolingual tuning. Furthermore, we find that only 40 multilingual examples in an English tuning set substantially improve multilingual instruction-following, both in seen and unseen languages during tuning. In general, we observe that models tuned on multilingual mixtures exhibit comparable or superior performance in several languages compared to monolingually tuned models, despite training on 10x fewer examples in those languages. Finally, we find that increasing the number of languages in the instruction tuning set from 1 to only 2, 3, or 4 increases cross-lingual generalization. Our results suggest that building massively multilingual instruction-tuned models can be done with only a very small set of multilingual instruction-responses.

ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding

We introduce ZeroSCROLLS, a zero-shot benchmark for natural language understanding over long texts, which contains only test sets, without training or development data. We adapt six tasks from the SCROLLS benchmark, and add four new datasets, including two novel information fusing tasks, such as aggregating the percentage of positive reviews. Using ZeroSCROLLS, we conduct a comprehensive evaluation of both open-source and closed large language models, finding that Claude outperforms ChatGPT, and that GPT-4 achieves the highest average score. However, there is still room for improvement on multiple open challenges in ZeroSCROLLS, such as aggregation tasks, where models struggle to pass the naive baseline. As the state of the art is a moving target, we invite researchers to evaluate their ideas on the live ZeroSCROLLS leaderboard

Causes and Cures for Interference in Multilingual Translation

Multilingual machine translation models can benefit from synergy between different language pairs, but also suffer from interference. While there is a growing number of sophisticated methods that aim to eliminate interference, our understanding of interference as a phenomenon is still limited. This work identifies the main factors that contribute to interference in multilingual machine translation. Through systematic experimentation, we find that interference (or synergy) are primarily determined by model size, data size, and the proportion of each language pair within the total dataset. We observe that substantial interference occurs mainly when the model is very small with respect to the available training data, and that using standard transformer configurations with less than one billion parameters largely alleviates interference and promotes synergy. Moreover, we show that tuning the sampling temperature to control the proportion of each language pair in the data is key to balancing the amount of interference between low and high resource language pairs effectively, and can lead to superior performance overall.

Efficient Long-Text Understanding with Short-Text Models

Transformer-based pretrained language models (LMs) are ubiquitous across natural language understanding, but cannot be applied to long sequences such as stories, scientific articles and long documents, due to their quadratic complexity. While a myriad of efficient transformer variants have been proposed, they are typically based on custom implementations that require expensive pretraining from scratch. In this work, we propose SLED: SLiding-Encoder and Decoder, a simple approach for processing long sequences that re-uses and leverages battle-tested short-text pretrained LMs. Specifically, we partition the input into overlapping chunks, encode each with a short-text LM encoder and use the pretrained decoder to fuse information across chunks (fusion-in-decoder). We illustrate through controlled experiments that SLED offers a viable strategy for long text understanding and evaluate our approach on SCROLLS, a benchmark with seven datasets across a wide range of language understanding tasks. We find that SLED is competitive with specialized models that are up to 50x larger and require a dedicated and expensive pretraining step.

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.

Instruction Induction: From Few Examples to Natural Language Task Descriptions

Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations by prompting them to generate a natural language instruction that fits the examples. To explore this ability, we introduce the instruction induction challenge, compile a dataset consisting of 24 tasks, and define a novel evaluation metric based on executing the generated instruction. We discover that, to a large extent, the ability to generate instructions does indeed emerge when using a model that is both large enough and aligned to follow instructions; InstructGPT achieves 65.7% of human performance in our execution-based metric, while the original GPT-3 model reaches only 9.8% of human performance. This surprising result suggests that instruction induction might be a viable learning paradigm in and of itself, where instead of fitting a set of latent continuous parameters to the data, one searches for the best description in the natural language hypothesis space.