As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

The COVID-19 pandemic created a deluge of questionable and contradictory scientific claims about drug efficacy -- an "infodemic" with lasting consequences for science and society. In this work, we argue that NLP models can help domain experts distill and understand the literature in this complex, high-stakes area. Our task is to automatically identify contradictory claims about COVID-19 drug efficacy. We frame this as a natural language inference problem and offer a new NLI dataset created by domain experts. The NLI framing allows us to create curricula combining existing datasets and our own. The resulting models are useful investigative tools. We provide a case study of how these models help a domain expert summarize and assess evidence concerning remdisivir and hydroxychloroquine.

Crop type maps are critical for tracking agricultural land use and estimating crop production. Remote sensing has proven an efficient and reliable tool for creating these maps in regions with abundant ground labels for model training, yet these labels remain difficult to obtain in many regions and years. NASA's Global Ecosystem Dynamics Investigation (GEDI) spaceborne lidar instrument, originally designed for forest monitoring, has shown promise for distinguishing tall and short crops. In the current study, we leverage GEDI to develop wall-to-wall maps of short vs tall crops on a global scale at 10 m resolution for 2019-2021. Specifically, we show that (1) GEDI returns can reliably be classified into tall and short crops after removing shots with extreme view angles or topographic slope, (2) the frequency of tall crops over time can be used to identify months when tall crops are at their peak height, and (3) GEDI shots in these months can then be used to train random forest models that use Sentinel-2 time series to accurately predict short vs. tall crops. Independent reference data from around the world are then used to evaluate these GEDI-S2 maps. We find that GEDI-S2 performed nearly as well as models trained on thousands of local reference training points, with accuracies of at least 87% and often above 90% throughout the Americas, Europe, and East Asia. Systematic underestimation of tall crop area was observed in regions where crops frequently exhibit low biomass, namely Africa and South Asia, and further work is needed in these systems. Although the GEDI-S2 approach only differentiates tall from short crops, in many landscapes this distinction goes a long way toward mapping the main individual crop types. The combination of GEDI and Sentinel-2 thus presents a very promising path towards global crop mapping with minimal reliance on ground data.

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language models has mostly focused on data preprocessing and differential privacy methods, both requiring re-training the underlying LM. We propose knowledge unlearning as an alternative method to reduce privacy risks for LMs post hoc. We show that simply performing gradient ascent on target token sequences is effective at forgetting them with little to no degradation of general language modeling performances for larger LMs; it sometimes even substantially improves the underlying LM with just a few iterations. We also find that sequential unlearning is better than trying to unlearn all the data at once and that unlearning is highly dependent on which kind of data (domain) is forgotten. By showing comparisons with a previous data preprocessing method and a decoding method known to mitigate privacy risks for LMs, we show that unlearning can give a stronger empirical privacy guarantee in scenarios where the data vulnerable to extraction attacks are known a priori while being much more efficient and robust. We release the code and dataset needed to replicate our results at https://github.com/joeljang/knowledge-unlearning.

Large language models have demonstrated the ability to generate both natural language and programming language text. Such models open up the possibility of multi-language code generation: could code generation models generalize knowledge from one language to another? Although contemporary code generation models can generate semantically correct Python code, little is known about their abilities with other languages. We propose MultiPL-E, a system for translating unit test-driven code generation benchmarks to new languages. We create the first massively multilingual code generation benchmark by using MultiPL-E to translate two popular Python code generation benchmarks to 18 additional programming languages. We use MultiPL-E to extend the HumanEval benchmark and MBPP benchmark to 18 languages that encompass a range of programming paradigms and popularity. Using these new parallel benchmarks, we evaluate the multi-language performance of three state-of-the-art code generation models: Codex, CodeGen, and InCoder. We find that Codex matches or even exceeds its performance on Python for several other languages. The range of programming languages represented in MultiPL-E allow us to explore the impact of language frequency and language features on model performance. Finally, the MultiPL-E approach of compiling code generation benchmarks to new programming languages is both scalable and extensible, making it straightforward to evaluate new models, benchmarks, and languages.

We study the problem of training a principal in a multi-agent general-sum game using reinforcement learning (RL). Learning a robust principal policy requires anticipating the worst possible strategic responses of other agents, which is generally NP-hard. However, we show that no-regret dynamics can identify these worst-case responses in poly-time in smooth games. We propose a framework that uses this policy evaluation method for efficiently learning a robust principal policy using RL. This framework can be extended to provide robustness to boundedly rational agents too. Our motivating application is automated mechanism design: we empirically demonstrate our framework learns robust mechanisms in both matrix games and complex spatiotemporal games. In particular, we learn a dynamic tax policy that improves the welfare of a simulated trade-and-barter economy by 15%, even when facing previously unseen boundedly rational RL taxpayers.

As a penetration tester or bug bounty hunter, you know the importance of having the right tools at your disposal. ChatGPT is a powerful AI assistant that can help streamline your workflow and improve your results. In this blog post, we will explore the features and capabilities of ChatGPT that make it an indispensable tool for anyone in the field of cybersecurity. Chat GPT (Generative Pretrained Transformer) is a natural language processing tool used to automate numerous cybersecurity jobs. Vulnerability testing and analysis, data analysis, and report generating are just a few of the major areas where Chat GPT might be especially valuable.

The world is in a climate crisis. With average global temperatures increasing every year, the threat of seasonal forest fires is becoming increasingly worse. In places like the Pacific Northwest, wildfire season causes extensive damage to woodlands, rural communities, and townships, destroying farmlands and infrastructure and forcing hundreds of thousands of residents to flee their homes. These fires also lead to terrible air quality in cities located hundreds (or even thousands) of miles away. For instance, in September of 2022, the city of Vancouver (British Columbia) was ranked as having the worst air quality in the world - per the Air Quality Index (AQI).

"Throughout 2021 and 2022, the world began to experiment with a massive influx of commercially available AI-assisted and AI-powered tools that can be used, whether knowingly or unknowingly, during the process of creating, researching, and innovating. Looking ahead to 2023, we will start witnessing the legal and regulatory impact of these tools." In general, the adoption of artificial intelligence (AI) and machine learning technologies has the potential to impact society in many ways. These technologies can automate tasks and make them more efficient, which can lead to job displacement and other economic impacts. They can also be used to make decisions that affect people's lives, such as in the criminal justice system or in hiring, which raises ethical concerns.

Artificial intelligence (AI), often recognized as machine intelligence, is an area of computer science that emphasizes developing and managing technology that can learn to make choices and can separately carry out transactions on behalf of humans. The banking, financial services, and insurance segments experience substantial expansion during the estimated period. A substantial amount of client data or transaction records are produced owing to the rising digital revolution in banking and the augmented use of mobile payment, real-time money transfers, e-banking, and mobile banking applications. The global Artificial Intelligence Service Market size was valued at USD 93.5 billion in 2021 growing at the CAGR of 38.1% from 2022 to 2032. Evolve Business Intelligence provides an in-dept research study that contains the ability to focus on the major market dynamics in several region across the globe.