One of the exciting capabilities of recent language models for dialog is their ability to independently search for relevant information to ground a given dialog response. However, obtaining training data to teach models how to issue search queries is time and resource consuming. In this work, we propose q2d: an automatic data generation pipeline that generates information-seeking dialogs from questions. We prompt a large language model (PaLM) to create conversational versions of question answering datasets, and use it to improve query generation models that communicate with external search APIs to ground dialog responses. Unlike previous approaches which relied on human written dialogs with search queries, our method allows to automatically generate query-based grounded dialogs with better control and scale. Our experiments demonstrate that: (1) For query generation on the QReCC dataset, models trained on our synthetically-generated data achieve 90%--97% of the performance of models trained on the human-generated data; (2) We can successfully generate data for training dialog models in new domains without any existing dialog data as demonstrated on the multi-hop MuSiQue and Bamboogle QA datasets. (3) We perform a thorough analysis of the generated dialogs showing that humans find them of high quality and struggle to distinguish them from human-written dialogs.

The 0/1 matrix factorization defines matrix products using logical AND and OR as product-sum operators, revealing the factors influencing various decision processes. Instances and their characteristics are arranged in rows and columns. Formulating matrix factorization as an energy minimization problem and exploring it with Simulated Annealing (SA) theoretically enables finding a minimum solution in sufficient time. However, searching for the optimal solution in practical time becomes problematic when the energy landscape has many plateaus with flat slopes. In this work, we propose a method to facilitate the solution process by applying a gradient to the energy landscape, using a rectified linear type cost function readily available in modern annealing machines. We also propose a method to quickly obtain a solution by updating the cost function's gradient during the search process. Numerical experiments were conducted, confirming the method's effectiveness with both noise-free artificial and real data.

Stable This paper presents a comparative analysis of existing nudity Diffusion safety checker is designed to prevent unsafe image classification techniques for classifying images based generation, while LAION safety checker works by filtering on the presence of nudity, with a focus on their application out unwanted images from the training set to prevent diffusion in content moderation. The evaluation focuses on models being trained on inappropriate images. These CNN-based models, vision transformer, and popular opensource safety checkers demonstrate the growing importance of developing safety checkers from Stable Diffusion and Largescale effective and accurate image classification systems Artificial Intelligence Open Network (LAION).

The rapid evolution of large language models (LLMs) necessitates effective benchmarks for evaluating their role knowledge, which is essential for establishing connections with the real world and providing more immersive interactions. This paper introduces RoleEval, a bilingual benchmark designed to assess the memorization, utilization, and reasoning capabilities of role knowledge. RoleEval comprises RoleEval-Global (including internationally recognized characters) and RoleEval-Chinese (including characters popular in China), with 6,000 Chinese-English parallel multiple-choice questions focusing on 300 influential people and fictional characters drawn from a variety of domains including celebrities, anime, comics, movies, TV series, games, and fiction. These questions cover basic knowledge and multi-hop reasoning abilities, aiming to systematically probe various aspects such as personal information, relationships, abilities, and experiences of the characters. To maintain high standards, we perform a hybrid quality check process combining automatic and human verification, ensuring that the questions are diverse, challenging, and discriminative. Our extensive evaluations of RoleEval across various open-source and proprietary large language models, under both the zero- and few-shot settings, reveal insightful findings. Notably, while GPT-4 outperforms other models on RoleEval-Global, Chinese LLMs excel on RoleEval-Chinese, highlighting significant knowledge distribution differences. We expect that RoleEval will highlight the significance of assessing role knowledge for foundation models across various languages and cultural settings.

Multimodal Sarcasm Understanding (MSU) has a wide range of applications in the news field such as public opinion analysis and forgery detection. However, existing MSU benchmarks and approaches usually focus on sentence-level MSU. In document-level news, sarcasm clues are sparse or small and are often concealed in long text. Moreover, compared to sentence-level comments like tweets, which mainly focus on only a few trends or hot topics (e.g., sports events), content in the news is considerably diverse. Models created for sentence-level MSU may fail to capture sarcasm clues in document-level news. To fill this gap, we present a comprehensive benchmark for Document-level Multimodal Sarcasm Understanding (DocMSU). Our dataset contains 102,588 pieces of news with text-image pairs, covering 9 diverse topics such as health, business, etc. The proposed large-scale and diverse DocMSU significantly facilitates the research of document-level MSU in real-world scenarios. To take on the new challenges posed by DocMSU, we introduce a fine-grained sarcasm comprehension method to properly align the pixel-level image features with word-level textual features in documents. Experiments demonstrate the effectiveness of our method, showing that it can serve as a baseline approach to the challenging DocMSU. Our code and dataset are available at https://github.com/Dulpy/DocMSU.

Large language models (LLMs) have shown impressive capabilities in various tasks, yet they still struggle with math reasoning. Despite efforts to optimize Chain-of-Thoughts (CoT) prompts and fine-tune LLMs, the potential of few-shot learning remains unexplored. In this work, we propose CoT-Influx, a novel approach pushing the boundaries of few-shot CoT learning to improve LLM math reasoning capabilities. CoT-Influx addresses the challenges of the selection of useful examples and limited number of examples due to restricted context window length. Inspired by our observation that natural language inputs contain many redundancy, we propose a coarse-to-fine pruner as a plug-and-play module for LLMs, which first identifies as many crucial CoT examples as possible and then further prunes unimportant tokens within the context window. To train the pruner, we collect a math reasoning dataset with diverse difficulty and steps, introduce a reward to measure both the input's effectiveness for math reasoning and token length constraints, and propose a novel training approach with reinforcement learning. As a result, CoT-Influx significantly outperforms CoT and few-shot prompting baselines across various LLMs (LLaMA2-7B, 13B, 70B) and 5 mathematical datasets, achieving up to 4.55% absolute improvements. Remarkably, without any fine-tuning, LLaMA2-70B with CoT-Influx surpasses GPT-3.5 and a wide range of larger LLMs (PaLM, Minerva, etc.) on the GSM8K.

Fact checking can be an effective strategy against misinformation, but its implementation at scale is impeded by the overwhelming volume of information online. Recent artificial intelligence (AI) language models have shown impressive ability in fact-checking tasks, but how humans interact with fact-checking information provided by these models is unclear. Here, we investigate the impact of fact-checking information generated by a popular large language model (LLM) on belief in, and sharing intent of, political news in a preregistered randomized control experiment. Although the LLM performs reasonably well in debunking false headlines, we find that it does not significantly affect participants' ability to discern headline accuracy or share accurate news. Subsequent analysis reveals that the AI fact-checker is harmful in specific cases: it decreases beliefs in true headlines that it mislabels as false and increases beliefs in false headlines that it is unsure about. On the positive side, the AI fact-checking information increases sharing intents for correctly labeled true headlines. When participants are given the option to view LLM fact checks and choose to do so, they are significantly more likely to share both true and false news but only more likely to believe false news. Our findings highlight an important source of potential harm stemming from AI applications and underscore the critical need for policies to prevent or mitigate such unintended consequences.

With El Niño slated to drop a warm, wet winter on most of the US in the coming months, everybody's going to need something good to read while the weather outside is frightful. Engadget's well-read staff have some suggestions: our favorite books of 2023! We've got a phenomenal assortment of genres and titles for you this year, from horror and true crime to rom-coms and fantasy adventures, here to provide months of entertainment for even the most voracious reader. I love horror movies but horror novels are kind of hit and miss for me. I was immediately pulled into Final Girl Support Group, though, which does a lot of winking and nodding at classic slasher flicks while creating a completely unique story. Grady Hendrix's novel doesn't satirize the final girl, but imagines what life might be like for them after the end of their movie. Each of the main characters is (loosely) based on the final girl of a classic slasher, though their storylines don't feel contrived or predictable. It reads like a fast-paced thriller but, like so many of the best horror movies, it's also a poignant reflection on trauma.

Revolt against the machines began at Swingers. And at Bob's Big Boy, where for weeks Drew Carey picked up the tab. Members of the Writers Guild of America, or WGA, met at both Los Angeles-area diners frequently during their 148-day strike, which hinged on protecting Hollywood's scribes from being overrun by the march of artificial intelligence. Members of the WGA were just a small part of the resistance. The Screen Actors Guild--American Federation of Television and Radio Artists, or SAG-AFTRA, soon joined them on the picket lines, together forming a formidable uprising against the perceived threat of AI.

Even if you believe, as some do, that the world has moved from Peak TV to Trough TV, there are still more shows released in any given year than any one person could consume (trust us, we tried). Between major networks, cable television channels, and streaming services, there's just too much to watch. You're bound to miss your new favorite binge-watch. Below are our picks for the best TV shows you might have missed in 2023. If you buy something using links in our stories, we may earn a commission. This helps support our journalism.