Prompt-based interfaces for Large Language Models (LLMs) have made prototyping and building AI-powered applications easier than ever before. However, identifying potential harms that may arise from AI applications remains a challenge, particularly during prompt-based prototyping. To address this, we present Farsight, a novel in situ interactive tool that helps people identify potential harms from the AI applications they are prototyping. Based on a user's prompt, Farsight highlights news articles about relevant AI incidents and allows users to explore and edit LLM-generated use cases, stakeholders, and harms. We report design insights from a co-design study with 10 AI prototypers and findings from a user study with 42 AI prototypers. After using Farsight, AI prototypers in our user study are better able to independently identify potential harms associated with a prompt and find our tool more useful and usable than existing resources. Their qualitative feedback also highlights that Farsight encourages them to focus on end-users and think beyond immediate harms. We discuss these findings and reflect on their implications for designing AI prototyping experiences that meaningfully engage with AI harms. Farsight is publicly accessible at: https://PAIR-code.github.io/farsight.

In this research short, we examine the potential of using GPT-4o, a state-of-the-art large language model (LLM) to undertake evidence synthesis and systematic assessment tasks. Traditional workflows for such tasks involve large groups of domain experts who manually review and synthesize vast amounts of literature. The exponential growth of scientific literature and recent advances in LLMs provide an opportunity to complementing these traditional workflows with new age tools. We assess the efficacy of GPT-4o to do these tasks on a sample from the dataset created by the Global Adaptation Mapping Initiative (GAMI) where we check the accuracy of climate change adaptation related feature extraction from the scientific literature across three levels of expertise. Our results indicate that while GPT-4o can achieve high accuracy in low-expertise tasks like geographic location identification, their performance in intermediate and high-expertise tasks, such as stakeholder identification and assessment of depth of the adaptation response, is less reliable. The findings motivate the need for designing assessment workflows that utilize the strengths of models like GPT-4o while also providing refinements to improve their performance on these tasks.

Today, hate speech classification from Arabic tweets has drawn the attention of several researchers. Many systems and techniques have been developed to resolve this classification task. Nevertheless, two of the major challenges faced in this context are the limited performance and the problem of imbalanced data. In this study, we propose a novel approach that leverages ensemble learning and semi-supervised learning based on previously manually labeled. We conducted experiments on a benchmark dataset by classifying Arabic tweets into 5 distinct classes: non-hate, general hate, racial, religious, or sexism. Experimental results show that: (1) ensemble learning based on pre-trained language models outperforms existing related works; (2) Our proposed data augmentation improves the accuracy results of hate speech detection from Arabic tweets and outperforms existing related works. Our main contribution is the achievement of encouraging results in Arabic hate speech detection.

The flourishing ecosystem centered around voice personal assistants (VPA), such as Amazon Alexa, has led to the booming of VPA apps. The largest app market Amazon skills store, for example, hosts over 200,000 apps. Despite their popularity, the open nature of app release and the easy accessibility of apps also raise significant concerns regarding security, privacy and quality. Consequently, various testing approaches have been proposed to systematically examine VPA app behaviors. To tackle the inherent lack of a visible user interface in the VPA app, two strategies are employed during testing, i.e., chatbot-style testing and model-based testing. The former often lacks effective guidance for expanding its search space, while the latter falls short in interpreting the semantics of conversations to construct precise and comprehensive behavior models for apps. In this work, we introduce Elevate, a model-enhanced large language model (LLM)-driven VUI testing framework. Elevate leverages LLMs' strong capability in natural language processing to compensate for semantic information loss during model-based VUI testing. It operates by prompting LLMs to extract states from VPA apps' outputs and generate context-related inputs. During the automatic interactions with the app, it incrementally constructs the behavior model, which facilitates the LLM in generating inputs that are highly likely to discover new states. Elevate bridges the LLM and the behavior model with innovative techniques such as encoding behavior model into prompts and selecting LLM-generated inputs based on the context relevance. Elevate is benchmarked on 4,000 real-world Alexa skills, against the state-of-the-art tester Vitas. It achieves 15% higher state space coverage compared to Vitas on all types of apps, and exhibits significant advancement in efficiency.

Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing the performance of models typically consist of model-centric evaluation setups with overly standardized data preprocessing. This paper demonstrates that such model-centric evaluations are biased, as real-world modeling pipelines often require dataset-specific preprocessing and feature engineering. Therefore, we propose a data-centric evaluation framework. We select 10 relevant datasets from Kaggle competitions and implement expert-level preprocessing pipelines for each dataset. We conduct experiments with different preprocessing pipelines and hyperparameter optimization (HPO) regimes to quantify the impact of model selection, HPO, feature engineering, and test-time adaptation. Our main findings are: 1. After dataset-specific feature engineering, model rankings change considerably, performance differences decrease, and the importance of model selection reduces. 2. Recent models, despite their measurable progress, still significantly benefit from manual feature engineering. This holds true for both tree-based models and neural networks. 3. While tabular data is typically considered static, samples are often collected over time, and adapting to distribution shifts can be important even in supposedly static data. These insights suggest that research efforts should be directed toward a data-centric perspective, acknowledging that tabular data requires feature engineering and often exhibits temporal characteristics.

This approach is partic ularly useful when designing AI systems for tasks where it is difficult to specify a precise reward function or when it is important to align the model's behaviour with certain human expectations and values. For instance, RLHF has notably improved language models for context - aware text generation (Ziegler et al. 2020) and taught robots to navigate cluttered environments (Henry et al. 2010) . RLHF is commonly employed in the later stages of fine - tuning models, particularly in the development of prominent Large Language Models (LLMs) like GPT - 3.5 or GPT - 4. Initially, these models undergo training using vast text corpora to grasp a broad range of language patterns and contexts. This foundational training is supplemented by task - specific fine - tuning, where the models are adjusted to excel in particular applications, such as understanding and generating dialogues. The refinement process is then furt her enhanced through RLHF.

An important issue with Large Language Models (LLMs) is their undesired ability to generate toxic language. In this work, we show that the neurons responsible for toxicity can be determined by their power to discriminate toxic sentences, and that toxic language can be mitigated by reducing their activation levels proportionally to this power. We propose AUROC adaptation (AurA), an intervention that can be applied to any pre-trained LLM to mitigate toxicity. As the intervention is proportional to the ability of each neuron to discriminate toxic content, it is free of any model-dependent hyperparameters. We show that AurA can achieve up to $2.2 \times$ reduction in toxicity with only a $0.72$ perplexity increase. We also show that AurA is effective with models of different scale (from 1.5B to 40B parameters), and its effectiveness in mitigating toxic language, while preserving common-sense zero-shot abilities, holds across all scales. AurA can be combined with pre-prompting strategies, boosting its average mitigation potential from $1.28\times$ to $2.35\times$. Moreover, AurA can counteract adversarial pre-prompts that maliciously elicit toxic content, making it an effective method for deploying safer and less toxic models.

Extensive previous research has focused on post-training knowledge editing (KE) for language models (LMs) to ensure that knowledge remains accurate and up-to-date. One desired property and open question in KE is to let edited LMs correctly handle ripple effects, where LM is expected to answer its logically related knowledge accurately. In this paper, we answer the question of why most KE methods still create messy ripple effects. We conduct extensive analysis and identify a salient indicator, GradSim, that effectively reveals when and why updated knowledge ripples in LMs. GradSim is computed by the cosine similarity between gradients of the original fact and its related knowledge. We observe a strong positive correlation between ripple effect performance and GradSim across different LMs, KE methods, and evaluation metrics. Further investigations into three counter-intuitive failure cases (Negation, Over-Ripple, Multi-Lingual) of ripple effects demonstrate that these failures are often associated with very low GradSim. This finding validates that GradSim is an effective indicator of when knowledge ripples in LMs.

Preference optimization techniques have become a standard final stage for training state-of-art large language models (LLMs). However, despite widespread adoption, the vast majority of work to-date has focused on first-class citizen languages like English and Chinese. This captures a small fraction of the languages in the world, but also makes it unclear which aspects of current state-of-the-art research transfer to a multilingual setting. In this work, we perform an exhaustive study to achieve a new state-of-the-art in aligning multilingual LLMs. We introduce a novel, scalable method for generating high-quality multilingual feedback data to balance data coverage. We establish the benefits of cross-lingual transfer and increased dataset size in preference training. Our preference-trained model achieves a 54.4% win-rate against Aya 23 8B, the current state-of-the-art multilingual LLM in its parameter class, and a 69.5% win-rate or higher against widely used models like Gemma-1.1-7B-it, Llama-3-8B-Instruct, Mistral-7B-Instruct-v0.3. As a result of our study, we expand the frontier of alignment techniques to 23 languages covering half of the world's population.

The past few years have produced a series of spectacular advances in the decoding of speech from brain activity. The engine of these advances has been the acquisition of labelled data, with increasingly large datasets acquired from single subjects. However, participants exhibit anatomical and other individual differences, and datasets use varied scanners and task designs. As a result, prior work has struggled to leverage data from multiple subjects, multiple datasets, multiple tasks, and unlabelled datasets. In turn, the field has not benefited from the rapidly growing number of open neural data repositories to exploit large-scale data and deep learning. To address this, we develop an initial set of neuroscience-inspired self-supervised objectives, together with a neural architecture, for representation learning from heterogeneous and unlabelled neural recordings. Experimental results show that representations learned with these objectives scale with data, generalise across subjects, datasets, and tasks, and are also learned faster than using only labelled data. In addition, we set new benchmarks for two foundational speech decoding tasks. Taken together, these methods now unlock the potential for training speech decoding models with orders of magnitude more existing data.