OpenAI on Thursday announced Sora, a brand new model that generates high-definition videos up to one minute in length from text prompts. Sora, which means "sky" in Japanese, won't be available to the general public any time soon. Instead, OpenAI is making it available to a small group of academics and researchers who will assess harm and its potential for misuse. "Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background," the company said on its website. "The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world."

We already know that OpenAI's chatbots can pass the bar exam without going to law school. Now, just in time for the Oscars, a new OpenAI app called Sora hopes to master cinema without going to film school. For now a research product, Sora is going out to a few select creators and a number of security experts who will red-team it for safety vulnerabilities. OpenAI plans to make it available to all wannabe auteurs at some unspecified date, but it decided to preview it in advance. Other companies, from giants like Google to startups like Runway, have already revealed text-to-video AI projects.

The model was also able to identify moments of humor. When asked by the researchers to find a funny moment in the Apollo transcript, it picked out when astronaut Mike Collins referred to Armstrong as "the Czar." (Probably not the best line, but you get the point). In another demonstration, the team uploaded a 44-minute silent film featuring Buster Keaton and asked the AI to identify what information was on a piece of paper that, at some point in the movie, is removed from a character's pocket. In less than a minute, the model found the scene and correctly recalled the text written on the paper. Researchers also repeated a similar task from the Apollo experiment, asking the model to find a scene in the film based on a drawing, which it completed.

Machine learning models often excel on in-distribution (ID) data but struggle with unseen out-of-distribution (OOD) inputs. Most techniques for improving OOD robustness are not applicable to settings where the model is effectively a black box, such as when the weights are frozen, retraining is costly, or the model is leveraged via an API. Test-time augmentation (TTA) is a simple post-hoc technique for improving robustness that sidesteps black-box constraints by aggregating predictions across multiple augmentations of the test input. TTA has seen limited use in NLP due to the challenge of generating effective natural language augmentations. In this work, we propose LLM-TTA, which uses LLM-generated augmentations as TTA's augmentation function. LLM-TTA outperforms conventional augmentation functions across sentiment, toxicity, and news classification tasks for BERT and T5 models, with BERT's OOD robustness improving by an average of 4.30 percentage points without regressing average ID performance. We explore selectively augmenting inputs based on prediction entropy to reduce the rate of expensive LLM augmentations, allowing us to maintain performance gains while reducing the average number of generated augmentations by 57.76%. LLM-TTA is agnostic to the task model architecture, does not require OOD labels, and is effective across low and high-resource settings. We share our data, models, and code for reproducibility.

Selecting high-quality pre-training data is important for creating capable language models, but existing methods rely on simple heuristics. We introduce QuRating, a method for selecting pre-training data that captures the abstract qualities of texts which humans intuitively perceive. In this paper, we investigate four qualities - writing style, required expertise, facts & trivia, and educational value. We find that LLMs are able to discern these qualities and observe that they are better at making pairwise judgments of texts than at rating the quality of a text directly. We train a QuRater model to learn scalar ratings from pairwise judgments, and use it to annotate a 260B training corpus with quality ratings for each of the four criteria. In our experiments, we select 30B tokens according to the different quality ratings and train 1.3B-parameter language models on the selected data. We find that it is important to balance quality and diversity, as selecting only the highest-rated documents leads to poor results. When we sample using quality ratings as logits over documents, our models achieve lower perplexity and stronger in-context learning performance than baselines. Beyond data selection, we use the quality ratings to construct a training curriculum which improves performance without changing the training dataset. We extensively analyze the quality ratings and discuss their characteristics, biases, and wider implications.

Exploring and quantifying semantic relatedness is central to representing language. It holds significant implications across various NLP tasks, including offering insights into the capabilities and performance of Large Language Models (LLMs). While earlier NLP research primarily focused on semantic similarity, often within the English language context, we instead investigate the broader phenomenon of semantic relatedness. In this paper, we present SemRel, a new semantic relatedness dataset collection annotated by native speakers across 14 languages:Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard Arabic, Punjabi, Spanish, and Telugu. These languages originate from five distinct language families and are predominantly spoken in Africa and Asia -- regions characterised by a relatively limited availability of NLP resources. Each instance in the SemRel datasets is a sentence pair associated with a score that represents the degree of semantic textual relatedness between the two sentences. The scores are obtained using a comparative annotation framework. We describe the data collection and annotation processes, related challenges when building the datasets, and their impact and utility in NLP. We further report experiments for each language and across the different languages.

Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles, where factual accuracy is paramount. In this work, we propose DELL that identifies three key stages in misinformation detection where LLMs could be incorporated as part of the pipeline: 1) LLMs could \emph{generate news reactions} to represent diverse perspectives and simulate user-news interaction networks; 2) LLMs could \emph{generate explanations} for proxy tasks (e.g., sentiment, stance) to enrich the contexts of news articles and produce experts specializing in various aspects of news understanding; 3) LLMs could \emph{merge task-specific experts} and provide an overall prediction by incorporating the predictions and confidence scores of varying experts. Extensive experiments on seven datasets with three LLMs demonstrate that DELL outperforms state-of-the-art baselines by up to 16.8\% in macro f1-score. Further analysis reveals that the generated reactions and explanations are greatly helpful in misinformation detection, while our proposed LLM-guided expert merging helps produce better-calibrated predictions.

LLM is known to provide factually inaccurate information that appears to be confident, i.e. hallucination. It is currently a major obstacle to the reliability and trustworthiness of LLM [13, 34, 21]. An essential step towards solving this problem is measuring hallucinations. However, this is challenging from a data perspective as existing metrics presume that benchmark datasets posses gold-standard answers, i.e. "best" or "correct" answers written by humans [16]. The requirement of such answers imposes two fundamental limitations on hallucination measurement: 1) hiring human annotators to produce gold-standard answers is costly in both time and money [4, 43, 38]; 2) gold-standard answers are prone to natural human errors [7, 6, 49]. To this end, we take a step forward and propose a framework which measures the LLM hallucinations without the requirement of gold-standard answers. Our framework is partially inspired by the literature on learning with noisy labels [23, 18, 19], where there are no ground-truth labels for verifying the quality of imperfect human annotations [43, 38, 20], detecting annotation errors [48, 26, 47], or training models robustly [42, 3, 17, 36, 39]. Our basic idea is simple: leveraging off-the-shelf and high-quality LLMs to generate answers that serve as a proxy for gold-standard answers. The primary challenge in such an approach is how to properly weigh the expertise of each LLM for a given question x, without a priori knowledge of the true (i.e.

Living things, computers, societies, and even books are part of a grand evolutionary struggle to survive. That struggle shapes nature, nations, religions, art, science, and you. What you think, feel, and do is determined by it. Darwinian evolution does not apply solely to the genes that are stored in DNA. Using the insights of Alan Turing and Richard Dawkins, we will see that it also applies to the memes we store in our brains and the information we store in our computers. The next time you run for president, fight a war, or just deal with the ordinary problems humans are heir to, perhaps this book will be of use. If you want to understand why and when you will die, or if you want to achieve greatness this book may help. If you are concerned about where the computer revolution is headed, this book may provide some answers.

The rise of large language models (LLMs) has drawn attention to the existence of "jailbreaks" that allow the models to be used maliciously. However, there is no standard benchmark for measuring the severity of a jailbreak, leaving authors of jailbreak papers to create their own. We show that these benchmarks often include vague or unanswerable questions and use grading criteria that are biased towards overestimating the misuse potential of low-quality model responses. Some jailbreak techniques make the problem worse by decreasing the quality of model responses even on benign questions: we show that several jailbreaking techniques substantially reduce the zero-shot performance of GPT-4 on MMLU. Jailbreaks can also make it harder to elicit harmful responses from an "uncensored" open-source model. We present a new benchmark, StrongREJECT, which better discriminates between effective and ineffective jailbreaks by using a higher-quality question set and a more accurate response grading algorithm. We show that our new grading scheme better accords with human judgment of response quality and overall jailbreak effectiveness, especially on the sort of low-quality responses that contribute the most to over-estimation of jailbreak performance on existing benchmarks. We release our code and data at https://github.com/alexandrasouly/strongreject.