The remarkable performance of large language models (LLMs) in content generation, coding, and common-sense reasoning has spurred widespread integration into many facets of society. However, integration of LLMs raises valid questions on their reliability and trustworthiness, given their propensity to generate hallucinations: plausible, factually-incorrect responses, which are expressed with striking confidence. Previous work has shown that hallucinations and other non-factual responses generated by LLMs can be detected by examining the uncertainty of the LLM in its response to the pertinent prompt, driving significant research efforts devoted to quantifying the uncertainty of LLMs. This survey seeks to provide an extensive review of existing uncertainty quantification methods for LLMs, identifying their salient features, along with their strengths and weaknesses. We present existing methods within a relevant taxonomy, unifying ostensibly disparate methods to aid understanding of the state of the art. Furthermore, we highlight applications of uncertainty quantification methods for LLMs, spanning chatbot and textual applications to embodied artificial intelligence applications in robotics. We conclude with open research challenges in uncertainty quantification of LLMs, seeking to motivate future research.

This study evaluates the performance of OpenAI's o1-preview model in higher-order cognitive domains, including critical thinking, systematic thinking, computational thinking, data literacy, creative thinking, logical reasoning, and scientific reasoning. Using established benchmarks, we compared the o1-preview models's performance to human participants from diverse educational levels. o1-preview achieved a mean score of 24.33 on the Ennis-Weir Critical Thinking Essay Test (EWCTET), surpassing undergraduate (13.8) and postgraduate (18.39) participants (z = 1.60 and 0.90, respectively). In systematic thinking, it scored 46.1, SD = 4.12 on the Lake Urmia Vignette, significantly outperforming the human mean (20.08, SD = 8.13, z = 3.20). For data literacy, o1-preview scored 8.60, SD = 0.70 on Merk et al.'s "Use Data" dimension, compared to the human post-test mean of 4.17, SD = 2.02 (z = 2.19). On creative thinking tasks, the model achieved originality scores of 2.98, SD = 0.73, higher than the human mean of 1.74 (z = 0.71). In logical reasoning (LogiQA), it outperformed humans with average 90%, SD = 10% accuracy versus 86%, SD = 6.5% (z = 0.62). For scientific reasoning, it achieved near-perfect performance (mean = 0.99, SD = 0.12) on the TOSLS,, exceeding the highest human scores of 0.85, SD = 0.13 (z = 1.78). While o1-preview excelled in structured tasks, it showed limitations in problem-solving and adaptive reasoning. These results demonstrate the potential of AI to complement education in structured assessments but highlight the need for ethical oversight and refinement for broader applications.

This paper provides a review of recent publications and working papers on ChatGPT and related Large Language Models (LLMs) in accounting and finance. The aim is to understand the current state of research in these two areas and identify potential research opportunities for future inquiry. We identify three common themes from these earlier studies. The first theme focuses on applications of ChatGPT and LLMs in various fields of accounting and finance. The second theme utilizes ChatGPT and LLMs as a new research tool by leveraging their capabilities such as classification, summarization, and text generation. The third theme investigates implications of LLM adoption for accounting and finance professionals, as well as for various organizations and sectors. While these earlier studies provide valuable insights, they leave many important questions unanswered or partially addressed. We propose venues for further exploration and provide technical guidance for researchers seeking to employ ChatGPT and related LLMs as a tool for their research.

Continuous Generalized Category Discovery (C-GCD) aims to continually discover novel classes from unlabelled image sets while maintaining performance on old classes. In this paper, we propose a novel learning framework, dubbed Neighborhood Commonality-aware Evolution Network (NCENet) that conquers this task from the perspective of representation learning. Concretely, to learn discriminative representations for novel classes, a Neighborhood Commonality-aware Representation Learning (NCRL) is designed, which exploits local commonalities derived neighborhoods to guide the learning of representational differences between instances of different classes. To maintain the representation ability for old classes, a Bi-level Contrastive Knowledge Distillation (BCKD) module is designed, which leverages contrastive learning to perceive the learning and learned knowledge and conducts knowledge distillation. Extensive experiments conducted on CIFAR10, CIFAR100, and Tiny-ImageNet demonstrate the superior performance of NCENet compared to the previous state-of-the-art method. Particularly, in the last incremental learning session on CIFAR100, the clustering accuracy of NCENet outperforms the second-best method by a margin of 3.09\% on old classes and by a margin of 6.32\% on new classes. Our code will be publicly available at \href{https://github.com/xjtuYW/NCENet.git}{https://github.com/xjtuYW/NCENet.git}. \end{abstract}

Subsequent The academic field of learning instruction-guided visual works leverage generic vision-language representations navigation can be generally categorized into high-level [18, 59, 61, 96, 97] to pretrain vision-language-action category-specific search and low-level language-guided policies [14, 16, 32, 34, 36, 60, 74, 81] (Figure 1b), finetuning navigation, depending on the granularity of language instruction, parameters for specific tasks while maintaining the in which the former emphasizes the exploration same model architecture. In this paper, we argue that the process, while the latter concentrates on following detailed essential difference between these tasks lies in the granularity textual commands. Despite the differing focuses of these of instruction, and the learning problems should be unified tasks, the underlying requirements of interpreting instructions, under the broader concept of language-guided visual comprehending the surroundings, and inferring action navigation (VLN), where the overarching goal is to create decisions remain consistent. This paper consolidates a versatile system that can interpret and execute arbitrary diverse navigation tasks into a unified and generic framework language instructions (Figure 1c).

The commonsense reasoning capabilities of vision-language models (VLMs), especially in abductive reasoning and defeasible reasoning, remain poorly understood. Most benchmarks focus on typical visual scenarios, making it difficult to discern whether model performance stems from keen perception and reasoning skills, or reliance on pure statistical recall. We argue that by focusing on atypical events in videos, clearer insights can be gained on the core capabilities of VLMs. Explaining and understanding such out-of-distribution events requires models to extend beyond basic pattern recognition and regurgitation of their prior knowledge. To this end, we introduce BlackSwanSuite, a benchmark for evaluating VLMs' ability to reason about unexpected events through abductive and defeasible tasks. Our tasks artificially limit the amount of visual information provided to models while questioning them about hidden unexpected events, or provide new visual information that could change an existing hypothesis about the event. We curate a comprehensive benchmark suite comprising over 3,800 MCQ, 4,900 generative and 6,700 yes/no tasks, spanning 1,655 videos. After extensively evaluating various state-of-the-art VLMs, including GPT-4o and Gemini 1.5 Pro, as well as open-source VLMs such as LLaVA-Video, we find significant performance gaps of up to 32% from humans on these tasks. Our findings reveal key limitations in current VLMs, emphasizing the need for enhanced model architectures and training strategies.

Large language models (LLMs) have transformed natural language processing, yet face challenges in specialized tasks such as simulating opinions on environmental policies. This paper introduces a novel fine-tuning approach that integrates socio-demographic data from the UK Household Longitudinal Study, uniquely using profiling factors, such as age, gender, income, education, and region. This method enhances the accuracy and representation of generated views. By emulating diverse synthetic profiles, the fine-tuned models significantly outperform pre-trained counterparts, achieving measurable improvements in capturing demographic nuances. Evaluation metrics, including Chi-Squared, Cosine Similarity, Jaccard Index, and KL-divergence, reveal a strong alignment between synthetic and real-world opinions. This work demonstrates the potential of fine-tuned LLMs tailored to societal contexts to enable more ethical and precise policy simulations. Its broader implications include deploying LLMs in domains like healthcare and education, fostering inclusive and data-driven decision-making in both research and practice.

This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based RL, policy-gradient methods, model-based methods, and various other topics (including a very brief discussion of RL+LLMs).

Unsupervised pretraining has been transformative in many supervised domains. However, applying such ideas to reinforcement learning (RL) presents a unique challenge in that fine-tuning does not involve mimicking task-specific data, but rather exploring and locating the solution through iterative self-improvement. In this work, we study how unlabeled prior trajectory data can be leveraged to learn efficient exploration strategies. While prior data can be used to pretrain a set of low-level skills, or as additional off-policy data for online RL, it has been unclear how to combine these ideas effectively for online exploration. Our method SUPE (Skills from Unlabeled Prior data for Exploration) demonstrates that a careful combination of these ideas compounds their benefits. Our method first extracts low-level skills using a variational autoencoder (VAE), and then pseudo-relabels unlabeled trajectories using an optimistic reward model, transforming prior data into high-level, task-relevant examples. Finally, SUPE uses these transformed examples as additional off-policy data for online RL to learn a high-level policy that composes pretrained low-level skills to explore efficiently. We empirically show that SUPE reliably outperforms prior strategies, successfully solving a suite of long-horizon, sparse-reward tasks. Code: https://github.com/rail-berkeley/supe.

The rise of large language models (LLMs) has highlighted the importance of prompt engineering as a crucial technique for optimizing model outputs. While experimentation with various prompting methods, such as Few-shot, Chain-of-Thought, and role-based techniques, has yielded promising results, these advancements remain fragmented across academic papers, blog posts and anecdotal experimentation. The lack of a single, unified resource to consolidate the field's knowledge impedes the progress of both research and practical application. This paper argues for the creation of an overarching framework that synthesizes existing methodologies into a cohesive overview for practitioners. Using a design-based research approach, we present the Prompt Canvas, a structured framework resulting from an extensive literature review on prompt engineering that captures current knowledge and expertise. By combining the conceptual foundations and practical strategies identified in prompt engineering, the Prompt Canvas provides a practical approach for leveraging the potential of Large Language Models. It is primarily designed as a learning resource for pupils, students and employees, offering a structured introduction to prompt engineering. This work aims to contribute to the growing discourse on prompt engineering by establishing a unified methodology for researchers and providing guidance for practitioners.