Recent advances in generative artificial intelligence (AI) have shown promise in accurately grading open-ended student responses. However, few prior works have explored grading handwritten responses due to a lack of data and the challenge of combining visual and textual information. In this work, we leverage state-of-the-art multi-modal AI models, in particular GPT-4o, to automatically grade handwritten responses to college-level math exams. Using real student responses to questions in a probability theory exam, we evaluate GPT-4o's alignment with ground-truth scores from human graders using various prompting techniques. We find that while providing rubrics improves alignment, the model's overall accuracy is still too low for real-world settings, showing there is significant room for growth in this task.

Large language models (LLMs) have recently shown significant potential in various biological tasks such as protein engineering and molecule design. These tasks typically involve black-box discrete sequence optimization, where the challenge lies in generating sequences that are not only biologically feasible but also adhere to hard fine-grained constraints. However, LLMs often struggle with such constraints, especially in biological contexts where verifying candidate solutions is costly and time-consuming. In this study, we explore the possibility of employing LLMs as highly-constrained bilevel optimizers through a methodology we refer to as Language Model Optimization with Margin Expectation (LLOME). This approach combines both offline and online optimization, utilizing limited oracle evaluations to iteratively enhance the sequences generated by the LLM. We additionally propose a novel training objective - Margin-Aligned Expectation (MargE) - that trains the LLM to smoothly interpolate between the reward and reference distributions. Lastly, we introduce a synthetic test suite that bears strong geometric similarity to real biophysical problems and enables rapid evaluation of LLM optimizers without time-consuming lab validation. Our findings reveal that, in comparison to genetic algorithm baselines, LLMs achieve significantly lower regret solutions while requiring fewer test function evaluations. However, we also observe that LLMs exhibit moderate miscalibration, are susceptible to generator collapse, and have difficulty finding the optimal solution when no explicit ground truth rewards are available. Large language models (LLMs) have recently shown significant promise on various biophysical optimization tasks, such as protein engineering and molecule design. These tasks are often formulated as black-box discrete sequence optimization problems, wherein a solver must attempt to output a discrete sequence x X that is feasible (i.e., a biologically plausible sequence) and that fulfills a number of strict constraints, such as containing specific motifs. Yet despite their many successes, LLMs often struggle to generate outputs that fulfill hard fine-grained constraints [31].

Artificial intelligence (AI), machine learning, and deep learning have become transformative forces in big data analytics and management, enabling groundbreaking advancements across diverse industries. This article delves into the foundational concepts and cutting-edge developments in these fields, with a particular focus on large language models (LLMs) and their role in natural language processing, multimodal reasoning, and autonomous decision-making. Highlighting tools such as ChatGPT, Claude, and Gemini, the discussion explores their applications in data analysis, model design, and optimization. The integration of advanced algorithms like neural networks, reinforcement learning, and generative models has enhanced the capabilities of AI systems to process, visualize, and interpret complex datasets. Additionally, the emergence of technologies like edge computing and automated machine learning (AutoML) democratizes access to AI, empowering users across skill levels to engage with intelligent systems. This work also underscores the importance of ethical considerations, transparency, and fairness in the deployment of AI technologies, paving the way for responsible innovation. Through practical insights into hardware configurations, software environments, and real-world applications, this article serves as a comprehensive resource for researchers and practitioners. By bridging theoretical underpinnings with actionable strategies, it showcases the potential of AI and LLMs to revolutionize big data management and drive meaningful advancements across domains such as healthcare, finance, and autonomous systems.

In this paper, we investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift, i.e., can LLMs generalize to domains that require specific knowledge such as medicine and law in a zero-shot fashion without additional in-domain training? To this end, we devise a series of experiments to explain the performance gap empirically. Our findings suggest that: (a) LLMs struggle with dataset demands of closed domains such as retrieving long answer spans; (b) Certain LLMs, despite showing strong overall performance, display weaknesses in meeting basic requirements as discriminating between domain-specific senses of words which we link to pre-processing decisions; (c) Scaling model parameters is not always effective for cross domain generalization; and (d) Closed-domain datasets are quantitatively much different than open-domain EQA datasets and current LLMs struggle to deal with them. Our findings point out important directions for improving existing LLMs.

This paper addresses the cost-efficiency aspect of Reinforcement Learning from Human Feedback (RLHF). RLHF leverages datasets of human preferences over outputs of large language models (LLM)s to instill human expectations into LLMs. Although preference annotation comes with a monetized cost, the economic utility of a preference dataset has not been considered by far. What exacerbates this situation is that, given complex intransitive or cyclic relationships in preference datasets, existing algorithms for fine-tuning LLMs are still far from capturing comprehensive preferences. This raises severe cost-efficiency concerns in production environments, where preference data accumulate over time. In this paper, we discuss the fine-tuning of LLMs as a monetized economy and introduce an auction mechanism to improve the efficiency of preference data collection in dollar terms. We show that introducing an auction mechanism can play an essential role in enhancing the cost-efficiency of RLHF, while maintaining satisfactory model performance. Experimental results demonstrate that our proposed auction-based protocol is cost-effective for fine-tuning LLMs concentrating on high-quality feedback.

Current RLHF frameworks for aligning large language models (LLMs) typically assume a fixed prompt distribution, which is sub-optimal and limits the scalability of alignment and generalizability of models. To address this, we introduce a general open-ended RLHF framework that casts alignment as an asymmetric game between two players: (i) a creator that generates increasingly informative prompt distributions using reward signals, and (ii) a solver that learns to produce more preferred responses on prompts produced by the creator. This framework of Evolving Alignment via Asymmetric Self-Play (eva), results in a simple and efficient approach that can utilize any existing RLHF algorithm for scalable alignment. eva outperforms state-of-the-art methods on widely-used benchmarks, without the need of any additional human crafted prompts. Specifically, eva improves the win rate of Gemma-2-9B-it on Arena-Hard from 51.6% to 60.1% with DPO, from 55.7% to 58.9% with SPPO, from 52.3% to 60.7% with SimPO, and from 54.8% to 60.3% with ORPO, surpassing its 27B version and matching claude-3-opus. This improvement is persistent even when new human crafted prompts are introduced. Finally, we show eva is effective and robust under various ablation settings.

In the real world, a learning-enabled system usually undergoes multiple cycles of model development to enhance the system's ability to handle difficult or emerging tasks. This continual model development process raises a significant issue that the model development for acquiring new or improving existing capabilities may inadvertently lose capabilities of the old model, also known as catastrophic forgetting. Existing continual learning studies focus on mitigating catastrophic forgetting by trading off performance on previous tasks and new tasks to ensure good average performance. However, they are inadequate for many applications especially in safety-critical domains, as failure to strictly preserve the good performance of the old model not only introduces safety risks and uncertainties but also imposes substantial expenses in the re-improving and re-validation of existing properties. To address this issue, we introduce model developmental safety as a guarantee of a learning system such that in the model development process the new model should strictly preserve the existing protected capabilities of the old model while improving its performance on target tasks. To ensure the model developmental safety, we present a retention-centric framework by formulating the model developmental safety as data-dependent constraints. Under this framework, we study how to develop a pretrained vision-language model, specifically the CLIP model, for acquiring new capabilities or improving existing capabilities of image classification. We propose an efficient constrained optimization algorithm with theoretical guarantee and use its insights to finetune a CLIP model with task-dependent heads for promoting the model developmental safety. Our experiments on improving vision perception capabilities on autonomous driving and scene recognition datasets demonstrate the efficacy of the proposed approach.

Did artificial intelligence begin to plateau in 2024, following a boom year in 2023? It depends on who you ask. Some say AI models that were released this year and can apparently reason more effectively than their predecessors show that the lofty goal of artificial general intelligence (AGI) is still on track, but not everyone is convinced. Certainly, tech firms have continued to talk up the hype. When it launched GPT-4 in 2023, OpenAI boasted that the model had "human-level" performance on professional tests…

BUILD LEGO CREATIONS: This innovative app is here to make custom Lego creation fun and accessible for everyone, whether you're a seasoned builder or just getting started. By using advanced artificial intelligence and mobile scanning technology, Brick My World opens up a world of creative possibilities. 'OUR HOLIDAY GIFT': OpenAI released its text-to-video artificial intelligence model, Sora, this week after the completion of its testing phase. The OpenAI logo is being displayed on a smartphone with the Sora text-to-video generator visible in the background in this photo illustration, taken in Brussels, Belgium, on February 16, 2024. GRANNY FIGHTS BACK: Daisy is an artificial intelligence-powered grandma developed by Virgin Media O2 to interact with scammers.

The battle for AI supremacy is heating up. Almost exactly a week after OpenAI made its o1 model available to the public, Google today is offering a preview of its next-generation Gemini 2.0 model. In a blog post attributed to Google CEO Sundar Pichai, the company says 2.0 is its most capable model yet, with the algorithm offering native support for image and audio output. "It will enable us to build new AI agents that bring us closer to our vision of a universal assistant," says Pichai. Google is doing something different with Gemini 2.0.