This work introduces the LLM Online Spatial-temporal Reconstruction (LLM-OSR) framework, which integrates Graph Signal Processing (GSP) and Large Language Models (LLMs) for online spatial-temporal signal reconstruction. The LLM-OSR utilizes a GSP-based spatial-temporal signal handler to enhance graph signals and employs LLMs to predict missing values based on spatiotemporal patterns. The performance of LLM-OSR is evaluated on traffic and meteorological datasets under varying Gaussian noise levels. Experimental results demonstrate that utilizing GPT-4-o mini within the LLM-OSR is accurate and robust under Gaussian noise conditions. The limitations are discussed along with future research insights, emphasizing the potential of combining GSP techniques with LLMs for solving spatiotemporal prediction tasks.

Despite advancements in Large Language Model (LLM) alignment, understanding the reasons behind LLM preferences remains crucial for bridging the gap between desired and actual behavior. LLMs often exhibit biases or tendencies that diverge from human preferences, such as favoring certain writing styles or producing overly verbose outputs. However, current methods for evaluating preference alignment often lack explainability, relying on coarse-grained comparisons. To address this, we introduce PROFILE (PRObing Factors of InfLuence for Explainability), a novel framework that uncovers and quantifies the influence of specific factors driving preferences. PROFILE's factor level analysis explains the 'why' behind human-model alignment and misalignment, offering insights into the direction of model improvement. We apply PROFILE to analyze human and LLM preferences across three tasks: summarization, helpful response generation, and document-based question-answering. Our factor level analysis reveals a substantial discrepancy between human and LLM preferences in generation tasks, whereas LLMs show strong alignment with human preferences in evaluation tasks. We demonstrate how leveraging factor level insights, including addressing misaligned factors or exploiting the generation-evaluation gap, can improve alignment with human preferences. This work underscores the importance of explainable preference analysis and highlights PROFILE's potential to provide valuable training signals, driving further improvements in human-model alignment.

This work provides the first theoretical analysis of training transformers to solve complex problems by recursively generating intermediate states, analogous to fine-tuning for chain-of-thought (CoT) reasoning. We consider training a one-layer transformer to solve the fundamental k-parity problem, extending the work on RNNs by Wies et al. (2023). We establish three key results: (1) any finite-precision gradient-based algorithm, without intermediate supervision, requires substantial iterations to solve parity with finite samples. Our findings, supported by numerical experiments, show that task decomposition and stepwise reasoning naturally arise from optimizing transformers with CoT; moreover, self-consistency checking can improve multistep reasoning ability, aligning with empirical studies of CoT. Large language models (LLMs) based on the transformer architecture (Vaswani et al., 2017) have achieved astounding success across a variety of natural language processing and machine learning tasks (see e.g. These failures are particularly evident in tasks requiring multi-hop reasoning or compounded logical steps (Sakarvadia et al., 2024). A promising approach to overcome these limitations is chain-of-thought (CoT) reasoning, where the model is prompted or fine-tuned to solve complex tasks step-by-step by explicitly making intermediate reasoning steps to arrive at the desired answers (Wei et al., 2022; Kojima et al., 2022). Since its discovery, CoT reasoning has been shown to significantly enhance the problem-solving capabilities of LLMs while also increasing the interpretability and trustworthiness of the reasoning process, and has spawned numerous prompting techniques (Liu et al., 2023; Qiao et al., 2023) and applications for a variety of downstream tasks including common-sense reasoning, mathematical problem-solving, and symbolic or multi-modal reasoning; see e.g.

With the rapid growth of the Natural Language Processing (NLP) field, a vast variety of Large Language Models (LLMs) continue to emerge for diverse NLP tasks. As more papers are published, researchers and developers face the challenge of information overload. Thus, developing a system that can automatically extract and organise key information about LLMs from academic papers is particularly important. The standard format for documenting information about LLMs is the LLM model card (\textbf{LLM-Card}). We propose a method for automatically generating LLM model cards from scientific publications. We use Named Entity Recognition (\textbf{NER}) and Relation Extraction (\textbf{RE}) methods that automatically extract key information about LLMs from the papers, helping researchers to access information about LLMs efficiently. These features include model \textit{licence}, model \textit{name}, and model \textit{application}. With these features, we can form a model card for each paper. We processed 106 academic papers by defining three dictionaries -- LLM's name, licence, and application. 11,051 sentences were extracted through dictionary lookup, and the dataset was constructed through manual review of the final selection of 129 sentences with a link between the name and the \textit{licence}, and 106 sentences with a link between the model name and the \textit{application}. The resulting resource is relevant for LLM card illustrations using relational knowledge graphs. Our code and findings can contribute to automatic LLM card generation. Data and code in \textsc{autoLLM-Card} will be shared and freely available at \url{https://github.com/shengwei-tian/dependency-parser-visualization}

Theory of Mind (ToM) refers to the cognitive ability to infer and attribute mental states to oneself and others. As large language models (LLMs) are increasingly evaluated for social and cognitive capabilities, it remains unclear to what extent these models demonstrate ToM across diverse languages and cultural contexts. In this paper, we introduce a comprehensive study of multilingual ToM capabilities aimed at addressing this gap. Our approach includes two key components: (1) We translate existing ToM datasets into multiple languages, effectively creating a multilingual ToM dataset and (2) We enrich these translations with culturally specific elements to reflect the social and cognitive scenarios relevant to diverse populations. We conduct extensive evaluations of six state-of-the-art LLMs to measure their ToM performance across both the translated and culturally adapted datasets. The results highlight the influence of linguistic and cultural diversity on the models' ability to exhibit ToM, and questions their social reasoning capabilities. This work lays the groundwork for future research into enhancing LLMs' cross-cultural social cognition and contributes to the development of more culturally aware and socially intelligent AI systems. All our data and code are publicly available.

Large Language Models (LLMs) herald a transformative era in artificial intelligence (AI). However, the expansive scale of data and parameters of LLMs requires high-demand computational and memory resources, restricting their accessibility to a broader range of users and researchers. This paper introduces an effective approach that enhances the operational efficiency and affordability of LLM inference. By utilizing transformer-based federated learning (FL) with model-parallel distributed training, our model efficiently distributes the computational loads and memory requirements across a network of participants. This strategy permits users, especially those with limited resources to train state-of-the-art LLMs collaboratively. We also innovate an incentive mechanism within the FL framework, rewarding constructive contributions and filtering out malicious activities, thereby safeguarding the integrity and reliability of the training process. Concurrently, we leverage memory hierarchy strategies and Singular Value Decomposition (SVD) on weight matrices to boost computational and memory efficiencies further. Our results, derived from formulaic analyses and numerical calculations, demonstrate significant optimization of resource use and democratize access to cutting-edge LLMs, ensuring that a wide scale of users can both contribute to and benefit from these advanced models.

Understanding the inner mechanisms of black-box foundation models (FMs) is essential yet challenging in artificial intelligence and its applications. Over the last decade, the long-running focus has been on their explainability, leading to the development of post-hoc explainable methods to rationalize the specific decisions already made by black-box FMs. However, these explainable methods have certain limitations in terms of faithfulness and resource requirement. Consequently, a new class of interpretable methods should be considered to unveil the underlying mechanisms of FMs in an accurate, comprehensive, heuristic, and resource-light way. This survey aims to review those interpretable methods that comply with the aforementioned principles and have been successfully applied to FMs. These methods are deeply rooted in machine learning theory, covering the analysis of generalization performance, expressive capability, and dynamic behavior. They provide a thorough interpretation of the entire workflow of FMs, ranging from the inference capability and training dynamics to their ethical implications. Ultimately, drawing upon these interpretations, this review identifies the next frontier research directions for FMs.

Multimodal large language models (MLLMs) act as essential interfaces, connecting humans with AI technologies in multimodal applications. However, current MLLMs face challenges in accurately interpreting object orientation in images due to inconsistent orientation annotations in training data, hindering the development of a coherent orientation understanding. To overcome this, we propose egocentric instruction tuning, which aligns MLLMs' orientation understanding with the user's perspective, based on a consistent annotation standard derived from the user's egocentric viewpoint. We first generate egocentric instruction data that leverages MLLMs' ability to recognize object details and applies prior knowledge for orientation understanding. Using this data, we perform instruction tuning to enhance the model's capability for accurate orientation interpretation. In addition, we introduce EgoOrientBench, a benchmark that evaluates MLLMs' orientation understanding across three tasks using images collected from diverse domains. Experimental results on this benchmark show that egocentric instruction tuning significantly improves orientation understanding without compromising overall MLLM performance. The instruction data and benchmark dataset are available on our project page at https://github.com/jhCOR/EgoOrientBench.

The widely-used, weight-only quantized large language models (LLMs), which leverage low-bit integer (INT) weights and retain floating-point (FP) activations, reduce storage requirements while maintaining accuracy. However, this shifts the energy and latency bottlenecks towards the FP activations that are associated with costly memory accesses and computations. Existing LLM accelerators focus primarily on computation optimizations, overlooking the potential of jointly optimizing FP computations and data movement, particularly for the dominant FP-INT GeMM operations in LLM inference. To address these challenges, we investigate the sensitivity of activation precision across various LLM modules and its impact on overall model accuracy. Based on our findings, we first propose the Anda data type: an adaptive data format with group-shared exponent bits and dynamic mantissa bit allocation. Secondly, we develop an iterative post-training adaptive precision search algorithm that optimizes the bit-width for different LLM modules to balance model accuracy, energy efficiency, and inference speed. Lastly, a suite of hardware optimization techniques is proposed to maximally exploit the benefits of the Anda format. These include a bit-plane-based data organization scheme, Anda-enhanced processing units with bit-serial computation, and a runtime bit-plane Anda compressor to simultaneously optimize storage, computation, and memory footprints. Our evaluations on FPINT GeMM operations show that Anda achieves a 2.4x speedup, 4.0x area efficiency, and 3.1x energy efficiency improvement on average for popular LLMs including OPT, LLaMA, and LLaMA-2 series over the GPU-like FP-FP baseline. Anda demonstrates strong adaptability across various application scenarios, accuracy requirements, and system performance, enabling efficient LLM inference across a wide range of deployment scenarios.

Large language models (LLMs) have demonstrated strong capabilities in text understanding and generation. However, they often lack factuality, producing a mixture of true and false information, especially in long-form generation. In this work, we investigates the factuality of long-form text generation across various large language models (LLMs), including GPT-4, Gemini-1.5-Pro, Our analysis reveals that factuality scores tend to decline in later sentences of the generated text, accompanied by a rise in the number of unsupported claims. Furthermore, we explore the effectiveness of different evaluation settings to assess whether LLMs can accurately judge the correctness of their own outputs: Self-Known (the percentage of supported atomic claims, decomposed from LLM outputs, that the corresponding LLMs judge as correct) and Self-Unknown (the percentage of unsupported atomic claims that the corresponding LLMs judge as incorrect). The results indicate that even advanced models like GPT-4 and Gemini-1.5-Pro Moreover, we find a correlation between higher Self-Known scores and improved factuality, while higher Self-Unknown scores are associated with lower factuality. These findings show the limitations of current LLMs in long-form generation, and provide valuable insights for improving factuality in long-form text generation. The long-context capabilities of large language models (LLMs) (OpenAI, 2023b; AI@Meta, 2024; Jiang et al., 2024; GeminiTeam, 2024; Anthropic, 2024) have seen significant advancements in recent years. Lots of work (Shaham et al., 2023; Bai et al., 2024; An et al., 2024; Zhang et al., 2024; Kuratov et al., 2024) have explored the ability of LLMs to handle long contexts, however, relatively few have examined their ability for long-form text generation.