Large language models (LLMs) are trained on vast amounts of data to generate natural language, enabling them to perform tasks like text summarization and question answering. These models have become popular in artificial intelligence (AI) assistants like ChatGPT and already play an influential role in how humans access information. However, the behavior of LLMs varies depending on their design, training, and use. In this paper, we uncover notable diversity in the ideological stance exhibited across different LLMs and languages in which they are accessed. We do this by prompting a diverse panel of popular LLMs to describe a large number of prominent and controversial personalities from recent world history, both in English and in Chinese. By identifying and analyzing moral assessments reflected in the generated descriptions, we find consistent normative differences between how the same LLM responds in Chinese compared to English. Similarly, we identify normative disagreements between Western and non-Western LLMs about prominent actors in geopolitical conflicts. Furthermore, popularly hypothesized disparities in political goals among Western models are reflected in significant normative differences related to inclusion, social inequality, and political scandals. Our results show that the ideological stance of an LLM often reflects the worldview of its creators. This raises important concerns around technological and regulatory efforts with the stated aim of making LLMs ideologically `unbiased', and it poses risks for political instrumentalization.

Recent advancements in Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. While these models excel in general complex reasoning tasks, they still face challenges in mathematical problem-solving and logical reasoning. To address these limitations, researchers have explored function calling abilities, allowing LLMs to execute provided functions and utilize their outputs for task completion. However, concentrating on specific tasks can be very inefficient for large-scale LLMs to be used, because of the expensive cost of training and inference stages they need in terms of computational resources. This study introduces a novel framework for training smaller language models in function calling, focusing on specific logical and mathematical reasoning tasks. The approach aims to improve performances of small-scale models for these tasks using function calling, ensuring a high level of accuracy. Our framework employs an agent that, given a problem and a set of callable functions, queries the LLM by injecting a description and examples of the usable functions into the prompt and managing their calls in a step-by-step reasoning chain. This process is used to create a dataset of correct and incorrect reasoning chain chat completions from a large-scale LLM. This dataset is used to train a smaller LLM using Reinforcement Learning from Human Feedback (RLHF), specifically employing the Direct Preference Optimization (DPO) technique. Experimental results demonstrate how the proposed approach balances the trade-off between model size and performance, improving the ability of function calling for reasoning tasks, in smaller models.

With models getting stronger, evaluations have grown more complex, testing multiple skills in one benchmark and even in the same instance at once. However, skill-wise performance is obscured when inspecting aggregate accuracy, under-utilizing the rich signal modern benchmarks contain. We propose an automatic approach to recover the underlying skills relevant for any evaluation instance, by way of inspecting model-generated rationales. After validating the relevance of rationale-parsed skills and inferring skills for $46$k instances over $12$ benchmarks, we observe many skills to be common across benchmarks, resulting in the curation of hundreds of skill-slices (i.e. sets of instances testing a common skill). Inspecting accuracy over these slices yields novel insights on model trade-offs: e.g., compared to GPT-4o and Claude 3.5 Sonnet, on average, Gemini 1.5 Pro is $18\%$ more accurate in "computing molar mass", but $19\%$ less accurate in "applying constitutional law", despite the overall accuracies of the three models differing by a mere $0.4\%$. Furthermore, we demonstrate the practical utility of our approach by showing that insights derived from skill slice analysis can generalize to held-out instances: when routing each instance to the model strongest on the relevant skills, we see a $3\%$ accuracy improvement over our $12$ dataset corpus. Our skill-slices and framework open a new avenue in model evaluation, leveraging skill-specific analyses to unlock a more granular and actionable understanding of model capabilities.

This paper explores the rapid development of a telephone call summarization system utilizing large language models (LLMs). Our approach involves initial experiments with prompting existing LLMs to generate summaries of telephone conversations, followed by the creation of a tailored synthetic training dataset utilizing stronger frontier models. We place special focus on the diversity of the generated data and on the ability to control the length of the generated summaries to meet various use-case specific requirements. The effectiveness of our method is evaluated using two state-of-the-art LLM-as-a-judge-based evaluation techniques to ensure the quality and relevance of the summaries. Our results show that fine-tuned Llama-2-7B-based summarization model performs on-par with GPT-4 in terms of factual accuracy, completeness and conciseness. Our findings demonstrate the potential for quickly bootstrapping a practical and efficient call summarization system.

The Internet has significantly expanded the potential for global collaboration, allowing millions of users to contribute to collective projects like Wikipedia. While prior work has assessed the success of online collaborations, most approaches are time-agnostic, evaluating success without considering its longevity. Research on the factors that ensure the long-term preservation of high-quality standards in online collaboration is scarce. In this study, we address this gap. We propose a novel metric, `Sustainable Success,' which measures the ability of collaborative efforts to maintain their quality over time. Using Wikipedia as a case study, we introduce the SustainPedia dataset, which compiles data from over 40K Wikipedia articles, including each article's sustainable success label and more than 300 explanatory features such as edit history, user experience, and team composition. Using this dataset, we develop machine learning models to predict the sustainable success of Wikipedia articles. Our best-performing model achieves a high AU-ROC score of 0.88 on average. Our analysis reveals important insights. For example, we find that the longer an article takes to be recognized as high-quality, the more likely it is to maintain that status over time (i.e., be sustainable). Additionally, user experience emerged as the most critical predictor of sustainability. Our analysis provides insights into broader collective actions beyond Wikipedia (e.g., online activism, crowdsourced open-source software), where the same social dynamics that drive success on Wikipedia might play a role. We make all data and code used for this study publicly available for further research.

Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel prototype-based model that provides fine-grained, sub-sentence level interpretability for text classification. ProtoLens uses a Prototype-aware Span Extraction module to identify relevant text spans associated with learned prototypes and a Prototype Alignment mechanism to ensure prototypes are semantically meaningful throughout training. By aligning the prototype embeddings with human-understandable examples, ProtoLens provides interpretable predictions while maintaining competitive accuracy. Extensive experiments demonstrate that ProtoLens outperforms both prototype-based and non-interpretable baselines on multiple text classification benchmarks. Code and data are available at \url{https://anonymous.4open.science/r/ProtoLens-CE0B/}.

The emergence of diffusion models has transformed synthetic media generation, offering unmatched realism and control over content creation. These advancements have driven innovation across fields such as art, design, and scientific visualization. However, they also introduce significant ethical and societal challenges, particularly through the creation of hyper-realistic images that can facilitate deepfakes, misinformation, and unauthorized reproduction of copyrighted material. In response, the need for effective detection mechanisms has become increasingly urgent. This review examines the evolving adversarial relationship between diffusion model development and the advancement of detection methods. We present a thorough analysis of contemporary detection strategies, including frequency and spatial domain techniques, deep learning-based approaches, and hybrid models that combine multiple methodologies. We also highlight the importance of diverse datasets and standardized evaluation metrics in improving detection accuracy and generalizability. Our discussion explores the practical applications of these detection systems in copyright protection, misinformation prevention, and forensic analysis, while also addressing the ethical implications of synthetic media. Finally, we identify key research gaps and propose future directions to enhance the robustness and adaptability of detection methods in line with the rapid advancements of diffusion models. This review emphasizes the necessity of a comprehensive approach to mitigating the risks associated with AI-generated content in an increasingly digital world.

Knowledge Graphs (KGs) can serve as reliable knowledge sources for question answering (QA) due to their structured representation of knowledge. Existing research on the utilization of KG for large language models (LLMs) prevalently relies on subgraph retriever or iterative prompting, overlooking the potential synergy of LLMs' step-wise reasoning capabilities and KGs' structural nature. In this paper, we present DoG (Decoding on Graphs), a novel framework that facilitates a deep synergy between LLMs and KGs. We first define a concept, well-formed chain, which consists of a sequence of interrelated fact triplets on the KGs, starting from question entities and leading to answers. We argue that this concept can serve as a principle for making faithful and sound reasoning for KGQA. To enable LLMs to generate well-formed chains, we propose graph-aware constrained decoding, in which a constraint derived from the topology of the KG regulates the decoding process of the LLMs. This constrained decoding method ensures the generation of well-formed chains while making full use of the step-wise reasoning capabilities of LLMs. Based on the above, DoG, a training-free approach, is able to provide faithful and sound reasoning trajectories grounded on the KGs. Experiments across various KGQA tasks with different background KGs demonstrate that DoG achieves superior and robust performance. DoG also shows general applicability with various open-source LLMs.

The advanced machine is about enhancing the quality of life for those who need assistance the most. Ariana Grande at the Fourth Annual Academy Museum Gala held at Academy Museum of Motion Pictures on Oct. 19, 2024 in Los Angeles, California. SOMETHING'WICKED': "Wicked" star Ariana Grande is uncertain about artificial intelligence after her co-star Cynthia Erivo felt insulted by fan edits of the poster for the upcoming musical. TECH INTERFERENCE: TikTok parent company ByteDance has confirmed it terminated an intern over the summer for allegedly sabotaging the training of an artificial intelligence model. A woman walks to cast her ballot after filling it in a privacy booth while voting in the gubernatorial election in Newark, New Jersey, on Nov. 2, 2021.

Google has been using artificial intelligence watermarking to automatically identify text generated by the company's Gemini chatbot, making it easier to distinguish AI-generated content from human-written posts. That watermark system could help prevent misuse of the AI chatbots for misinformation and disinformation – not to mention cheating in school and business settings. Now, the tech company is making an open-source version of its technique available so that other generative AI developers can similarly watermark the output from their own large language models, says Pushmeet Kohli at Google DeepMind, the company's AI research team, which combines the former Google Brain and DeepMind labs. "While SynthID isn't a silver bullet for identifying AI-generated content, it is an important building block for developing more reliable AI identification tools," he says. Google creates self-replicating life from digital'primordial soup' Independent researchers voiced similar optimism.