The widespread use of social media has led to a surge in popularity for automated methods of analyzing public opinion. Supervised methods are adept at text categorization, yet the dynamic nature of social media discussions poses a continual challenge for these techniques due to the constant shifting of the focus. On the other hand, traditional unsupervised methods for extracting themes from public discourse, such as topic modeling, often reveal overarching patterns that might not capture specific nuances. Consequently, a significant portion of research into social media discourse still depends on labor-intensive manual coding techniques and a human-in-the-loop approach, which are both time-consuming and costly. In this work, we study the problem of discovering arguments associated with a specific theme. We propose a generic LLMs-in-the-Loop strategy that leverages the advanced capabilities of Large Language Models (LLMs) to extract latent arguments from social media messaging. To demonstrate our approach, we apply our framework to contentious topics. We use two publicly available datasets: (1) the climate campaigns dataset of 14k Facebook ads with 25 themes and (2) the COVID-19 vaccine campaigns dataset of 9k Facebook ads with 14 themes. Additionally, we design a downstream task as stance prediction by leveraging talking points in climate debates. Furthermore, we analyze demographic targeting and the adaptation of messaging based on real-world events.

Learning from human preferences is crucial for language models (LMs) to effectively cater to human needs and societal values. Previous research has made notable progress by leveraging human feedback to follow instructions. However, these approaches rely primarily on online learning techniques like Proximal Policy Optimization (PPO), which have been proven unstable and challenging to tune for language models. Moreover, PPO requires complex distributed system implementation, hindering the efficiency of large-scale distributed training. In this study, we propose an offline learning from human feedback framework to align LMs without interacting with environments. Specifically, we explore filtering alignment (FA), reward-weighted regression (RWR), and conditional alignment (CA) to align language models to human preferences. By employing a loss function similar to supervised fine-tuning, our methods ensure more stable model training than PPO with a simple machine learning system~(MLSys) and much fewer (around 9\%) computing resources. Experimental results demonstrate that conditional alignment outperforms other offline alignment methods and is comparable to PPO.

During the last stage of RLHF, a large language model is aligned to human intents via PPO training, a process that generally requires large-scale computational resources. In this technical report, we empirically investigate an efficient implementation of RLHF using low-rank adaptation (LoRA), which allows us to align the LLaMA 7B checkpoint on the Alpaca dataset (Taori et al., 2023) using only two A100 GPUs instead of the eight required for full model fine-tuning. Despite tuning only 0.2% of LLaMA 7B's parameters, our implementation achieves better performance than the publicly-released AlpacaFarm checkpoint (Dubois et al., 2023) with full model fine-tuning. Next, we analyze several configurations of our LoRA-based PPO implementation, varying the form of the KL regularization term in the training objective. We find that (1) removing this penalty term does not harm performance on the AlpacaFarm evaluation set under our LoRA setup; (2) other regularizers, such as Jensen-Shannon divergence, lead to improved performance; and (3) while PPO training negatively impacts the factuality of model-generated responses, training with LoRA largely mitigates this effect. We release our code and pretrained checkpoints to facilitate future research on more efficient RLHF.

Move to Leeds and benefit from the jobs boom, says Melissa Berthelot, boss of medical appliance maker WarnerPatch, who relocated her business from London two years ago to benefit from a burgeoning deep tech industry in the West Yorkshire city. With skilled data science and software engineers in short supply across the south-east – and most other parts of the country – Leeds has proved a happy hunting ground for Berthelot, an engineer turned chief executive who used the first lockdown to make the jump north. Deep tech refers to sectors including artificial intelligence, robotics and bio-technologies. Its Blade Runner-like image may seem worlds away from the Emmerdale village tour on offer just west of town, but Leeds is managing to straddle old and new as it jumps up the UK rankings for job creation and productivity. The city has gained a reputation for developing the skilled staff and financial muscle needed to fund startups and innovation, especially in healthcare, but also in the city's more traditional areas of expertise – financial and legal services, manufacturing and retail.

Artificial intelligence (AI) will create new job opportunities, not destroy them. AI will displace some jobs but will create new ones. The main aim of this article is intended to focus the minds of our political and business leaders as they consider what strategies to pursue to grow the economy (GDP), business activity and stimulate job creation whilst also taking into account the growing challenges of the environment with climate change mitigation increasingly on the agenda. Let's start by reviewing the types of AI and where we are now. Narrow AI: the field of AI where the machine is designed to perform a single task and the machine gets very good at performing that particular task.

The decisions that we make now and in the near future will set the tone for the rest of the decade including how artificial intelligence (AI) may develop and how we will use it. It will require enlightened leadership to maximise the benefit for human society. This article is focused on providing a moment of reflection in terms of where we are and where we are going from a policy and philosophical perspective and to serve as a prelude to a more technical article on the next generation of AI that will follow. Positive use case potential for AI includes the fight against Covid -19. For example The Lancet published an article authored by Zhou et al. entitled "Artificial Intelligence in COVID-19 drug repurposing" and state that " In this Review, we introduce guidelines on how to use AI for accelerating drug repurposing or repositioning, for which AI approaches are not just formidable but are also necessary. We discuss how to use AI models in precision medicine, and as an example, how AI models can accelerate COVID-19 drug repurposing."

The decisions that we make now and in the near future will set the tone for the rest of the decade including how artificial intelligence (AI) may develop and how we will use it. It will require enlightened leadership to maximise the benefit for human society. This article is focused on providing a moment of reflection in terms of where we are and where we are going from a policy and philosophical perspective and to serve as a prelude to a more technical article on the next generation of AI that will follow. Positive use case potential for AI includes the fight against Covid -19. For example The Lancet published an article authored by Zhou et al. entitled "Artificial Intelligence in COVID-19 drug repurposing" and state that " In this Review, we introduce guidelines on how to use AI for accelerating drug repurposing or repositioning, for which AI approaches are not just formidable but are also necessary. We discuss how to use AI models in precision medicine, and as an example, how AI models can accelerate COVID-19 drug repurposing."

The year of 2020 has proved to be a challenging year defined mostly across the world by a global pandemic and as a result an increasing shift towards digital. The decisions that we make now and in the near future will set the tone for the rest of the decade including how AI may develop and how we will use it. It will require enlightened leadership to maximise the benefit for human society. This article is focused on providing a moment of reflection in terms of where we are and where we are going from a policy and philosophical perspective and to serve as a prelude to a more technical article on the next generation of AI that will follow. Positive use case potential for AI includes the fight against Covid -19.

The story of automation in America has long been told in shuttered factories and declining Midwestern cities. But the latest wave of advancements in artificial intelligence may be bring the prospect of machine replacement beyond blue collar work. Developers are creating algorithms that promise to take over vast amounts of work in white collar fields like law and medicine, potentially upending traditionally high-status fields. For people in those once-secure positions, the questions are whose jobs may be changed, how soon, and what new opportunities may arise to take their place. Knowledge work that involves repetitive tasks or large amounts of data, such as lawyers' often arduous document discovery process, is particularly ripe for disruption from AI, experts say.

An army of robots now scrub floors, grow microgreens and flip burgers. Due to advances in artificial intelligence, computers will supposedly take over much more of the service sector in the coming decade, including jobs in law, finance and medicine that require years of education and training. Will automation-induced job loss tear society apart? The question has even influenced the US presidential race. Candidate Andrew Yang blames automation for a long-simmering crisis of underemployment.