If you've always wondered what it takes to be a badass, a new study reveals the strict criteria. Following questionnaires involving over 2,000 people, researchers in the US have officially improved on the dictionary definition of the term. A badass has an'outer toughness' (consisting of physical strength, a'formidable presence', or both), an inner toughness (such as moral resilience and courage), or both. That's why'radically' different men and women – ranging from peace advocates to fierce warriors – can be considered badasses, according to the experts. Famous badasses include Genghis Khan (AD 1162 to 1227), the brutal founder of the Mongol Empire responsible for the deaths of around 40 million people, they say.

In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context. This issue we have termed the false negative problem refers to the phenomenon where LLMs are predisposed to return negative judgments when assessing the correctness of a statement given the context. In experiments involving pairs of statements that contain the same information but have contradictory factual directions, we observe that LLMs exhibit a bias toward false negatives. Specifically, the model presents greater overconfidence when responding with False. Furthermore, we analyze the relationship between the false negative problem and context and query rewriting and observe that both effectively tackle false negatives in LLMs.

Dynamic retrieval augmented generation (RAG) paradigm actively decides when and what to retrieve during the text generation process of Large Language Models (LLMs). There are two key elements of this paradigm: identifying the optimal moment to activate the retrieval module (deciding when to retrieve) and crafting the appropriate query once retrieval is triggered (determining what to retrieve). However, current dynamic RAG methods fall short in both aspects. Firstly, the strategies for deciding when to retrieve often rely on static rules. Moreover, the strategies for deciding what to retrieve typically limit themselves to the LLM's most recent sentence or the last few tokens, while the LLM's real-time information needs may span across the entire context. To overcome these limitations, we introduce a new framework, DRAGIN, i.e., Dynamic Retrieval Augmented Generation based on the real-time Information Needs of LLMs. Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's real-time information needs during the text generation process. We evaluate DRAGIN along with existing methods comprehensively over 4 knowledge-intensive generation datasets. Experimental results show that DRAGIN achieves superior performance on all tasks, demonstrating the effectiveness of our method. We have open-sourced all the code, data, and models in GitHub: https://github.com/oneal2000/DRAGIN/tree/main

Earlier this month, Meta (the corporation formerly known as Facebook) released an AI chatbot with the innocuous name Blenderbot that anyone in the US can talk with. Immediately, users all over the country started posting the AI's takes condemning Facebook, while pointing out that, as has often been the case with language models like this one, it's really easy to get the AI to spread racist stereotypes and conspiracy theories. When I played with Blenderbot, I definitely saw my share of bizarre AI-generated conspiracy theories, like one about how big government is suppressing the true Bible, plus plenty of horrifying moral claims. But that wasn't what surprised me. We know language models, even advanced ones, still struggle with bias and truthfulness.

Genghis Khan got his dying wish: despite attempts by archaeologists and scientists to find the Mongolian ruler's final resting place, the location remains a secret 800 years after his death. The search for his tomb, though, has inspired an innovative project that could help protect polar bears. "I randomly tuned into the radio one night and heard an expert talking about the use of synthetic aperture radar [SAR] to look for Genghis Khan's tomb," says Tom Smith, associate professor in plant and wildlife sciences at Brigham Young University (BYU) in Utah. "They were using SAR to penetrate layers of forest canopy in upper Mongolia, looking for the ruins of a burial structure." Talking to engineers, including BYU's Dr David Long, Smith learned that SAR is used by the military to detect enemy camps, tanks and vehicles hidden beneath camouflage and is being studied as a potential tool for finding avalanche survivors.

In humans, the profound biological differences that exist between the sexes mean that a single male is physically capable of having far more children than is a single female. Women carry unborn children for nine months and often nurse them for several years prior to having additional children.1 Men, meanwhile, are able to procreate while investing far less time in the bearing and early rearing of each child. So it is that, as measured by the contribution to the next generation, powerful men have the potential to have a far greater impact than powerful women, and we can see this in genetic data. The great variability among males in the number of offspring produced means that by searching for genomic signatures of past variability in the number of children men have had, we can obtain genetic insights into the degree of social inequality in society as a whole, and not just between males and females. An extraordinary example of this is provided by the inequality in the number of male offspring that seems to have characterized the empire established by Genghis Khan, who ruled lands stretching from China to the Caspian Sea. After his death in 1227, his successors, including several of his sons and grandsons, extended the Mongol Empire even farther--to Korea in the east, to central Europe in the west, and to Tibet in the south.