This work presents a custom approach to developing a domain specific knowledge assistant for sustainability reporting using the International Financial Reporting Standards (IFRS). In this domain, there is no publicly available question-answer dataset, which has impeded the development of a high-quality chatbot to support companies with IFRS reporting. The two key contributions of this project therefore are: (1) A high-quality synthetic question-answer (QA) dataset based on IFRS sustainability standards, created using a novel generation and evaluation pipeline leveraging Large Language Models (LLMs). This comprises 1,063 diverse QA pairs that address a wide spectrum of potential user queries in sustainability reporting. Various LLM-based techniques are employed to create the dataset, including chain-of-thought reasoning and few-shot prompting. A custom evaluation framework is developed to assess question and answer quality across multiple dimensions, including faithfulness, relevance, and domain specificity. The dataset averages a score range of 8.16 out of 10 on these metrics. (2) Two architectures for question-answering in the sustainability reporting domain - a RAG pipeline and a fully LLM-based pipeline. The architectures are developed by experimenting, fine-tuning, and training on the QA dataset. The final pipelines feature an LLM fine-tuned on domain specific data and an industry classification component to improve the handling of complex queries. The RAG architecture achieves an accuracy of 85.32% on single-industry and 72.15% on cross-industry multiple-choice questions, outperforming the baseline approach by 4.67 and 19.21 percentage points, respectively. The LLM-based pipeline achieves an accuracy of 93.45% on single-industry and 80.30% on cross-industry multiple-choice questions, an improvement of 12.80 and 27.36 percentage points over the baseline, respectively.

Large language models (LLMs) (Brown et al., 2020; Touvron et al., 2023a; Liu et al., 2024a; Yang et al., 2024a) have been widely integrated into various real-world applications to assist human users, but their safety is found to be vulnerable toward jailbreak attacks (Wei et al., 2023). With carefully crafted adversarial prompts, one can "jailbreak" the safety mechanism of LLMs and induce arbitrary harmful behaviors (Zou et al., 2023; Chao et al., 2023; Liu et al., 2024b). To address this challenge, recent studies (Xhonneux et al., 2024; Mazeika et al., 2024; Yu et al., 2024; Casper et al., 2024) have proposed performing safety alignment through adversarial training (AT) (Madry et al., 2018) to enhance LLMs' robustness against jailbreaking. A standard AT for LLMs would train them on harmful adversarial prompts synthesized by strong jailbreak attacks to learn to refuse these harmful instructions (Mazeika et al., 2024). In such AT, the length of synthesized adversarial prompts used for model training is critical to the final jailbreak robustness of LLMs. Anil et al. (2024) and Xu et al. (2024) have shown that longer adversarial prompts enjoy stronger jailbreaking abilities. Thus, it is reasonable to deduce that performing AT with longer adversarial prompts can help LLMs achieve stronger robustness to defend against "long-length" jailbreak attacks. However, synthesizing long-length adversarial prompts in adversarial training is usually time-consuming since it requires solving discrete optimization problems in high-dimensional spaces. This may limit the application of AT in LLMs' safety alignment and further raises the following research question: How will the adversarial prompt length during AT affect trained LLMs' robustness against jailbreaking with different prompt lengths? S. Fu and D. Wang are with the Division of Computer, Electrical and Mathematical Science and Engineering (CEMSE) at the King Abdullah University of Science and Technology, Thuwal 23955, KSA.

Recent Large Language Models (LLMs) have demonstrated satisfying general instruction following ability. However, small LLMs with about 7B parameters still struggle fine-grained format following (e.g., JSON format), which seriously hinder the advancements of their applications. Most existing methods focus on benchmarking general instruction following while overlook how to improve the specific format following ability for small LLMs. Besides, these methods often rely on evaluations based on advanced LLMs (e.g., GPT-4), which can introduce the intrinsic bias of LLMs and be costly due to the API calls. In this paper, we first curate a fully verifiable format following dataset VFF. In contrast to existing works often adopting external LLMs for instruction-following validations, every sample of VFF can be easily validated with a Python function. Further, we propose to leverage this verifiable feature to synthesize massive data for progressively training small LLMs, in order to improve their format following abilities. Experimental results highlight the prevalent limitations in the format following capabilities of 7B level open-source LLMs and demonstrate the effectiveness of our method in enhancing this essential ability.

Large language models have revolutionized natural language processing but face significant challenges of high storage and runtime costs, due to the transformer architecture's reliance on self-attention, particularly the large Key-Value (KV) cache for long-sequence inference. Recent efforts to reduce KV cache size by pruning less critical entries based on attention weights remain empirical and lack formal grounding. This paper presents a formal study on identifying critical KV cache entries by analyzing attention output perturbation. Our analysis reveals that, beyond attention weights, the value states within KV entries and pretrained parameter matrices are also crucial. Based on this, we propose a perturbation-constrained selection algorithm that optimizes the worst-case output perturbation to identify critical entries. Evaluations on the Needle-in-a-Haystack test and Longbench benchmark show our algorithm enhances state-of-the-art cache eviction methods. Further empirical analysis confirms that our algorithm achieves lower output perturbations in over 92% attention heads in Llama model, thereby providing a significant improvement over existing methods.

Recent advancements in Retrieval-Augmented Generation (RAG) have shown remarkable performance in enhancing response accuracy and relevance by integrating external knowledge into generative models. However, existing RAG methods primarily focus on providing text-only answers, even in multimodal retrieval-augmented generation scenarios. In this work, we introduce the Multimodal Retrieval-Augmented Multimodal Generation (MRAMG) task, which aims to generate answers that combine both text and images, fully leveraging the multimodal data within a corpus. Despite the importance of this task, there is a notable absence of a comprehensive benchmark to effectively evaluate MRAMG performance. To bridge this gap, we introduce the MRAMG-Bench, a carefully curated, human-annotated dataset comprising 4,346 documents, 14,190 images, and 4,800 QA pairs, sourced from three categories: Web Data, Academic Papers, and Lifestyle. The dataset incorporates diverse difficulty levels and complex multi-image scenarios, providing a robust foundation for evaluating multimodal generation tasks. To facilitate rigorous evaluation, our MRAMG-Bench incorporates a comprehensive suite of both statistical and LLM-based metrics, enabling a thorough analysis of the performance of popular generative models in the MRAMG task. Besides, we propose an efficient multimodal answer generation framework that leverages both LLMs and MLLMs to generate multimodal responses. Our datasets are available at: https://huggingface.co/MRAMG.

Traditional autonomous driving systems often struggle with reasoning in complex, unexpected scenarios due to limited comprehension of spatial relationships. In response, this study introduces a Large Language Model (LLM)-based Autonomous Driving (AD) assistance system that integrates a vision adapter and an LLM reasoning module to enhance visual understanding and decision-making. The vision adapter, combining YOLOv4 and Vision Transformer (ViT), extracts comprehensive visual features, while GPT-4 enables human-like spatial reasoning and response generation. Experimental evaluations with 45 experienced drivers revealed that the system closely mirrors human performance in describing situations and moderately aligns with human decisions in generating appropriate responses.

Recent decades have witnessed remarkable advancements in artificial intelligence (AI), including large language models (LLMs), image and video generative models, and embodied AI systems. These advancements have led to an explosive increase in the demand for computational power, challenging the limits of Moore's Law. Optical lithography, a critical technology in semiconductor manufacturing, faces significant challenges due to its high costs. To address this, various lithography simulators have been developed. However, many of these simulators are limited by their inadequate photoresist modeling capabilities. This paper presents TorchResist, an open-source, differentiable photoresist simulator.TorchResist employs an analytical approach to model the photoresist process, functioning as a white-box system with at most twenty interpretable parameters. Leveraging modern differentiable programming techniques and parallel computing on GPUs, TorchResist enables seamless co-optimization with other tools across multiple related tasks. Our experimental results demonstrate that TorchResist achieves superior accuracy and efficiency compared to existing solutions. The source code is publicly available.

Healthcare systems are struggling to meet the growing demand for neurological care, with challenges particularly acute in Alzheimer's disease and related dementias (ADRD). While artificial intelligence research has often focused on identifying patterns beyond human perception, implementing such predictive capabilities remains challenging as clinicians cannot readily verify insights they cannot themselves detect. We propose that large language models (LLMs) offer more immediately practical applications by enhancing clinicians' capabilities in three critical areas: comprehensive data collection, interpretation of complex clinical information, and timely application of relevant medical knowledge. These challenges stem from limited time for proper diagnosis, growing data complexity, and an overwhelming volume of medical literature that exceeds any clinician's capacity to fully master. We present a framework for responsible AI integration that leverages LLMs' ability to communicate effectively with both patients and providers while maintaining human oversight. This approach prioritizes standardized, high-quality data collection to enable a system that learns from every patient encounter while incorporating the latest clinical evidence, continuously improving care delivery. We begin to address implementation challenges and initiate important discussions around ethical considerations and governance needs. While developed for ADRD, this roadmap provides principles for responsible AI integration across neurology and other medical specialties, with potential to improve diagnostic accuracy, reduce care disparities, and advance clinical knowledge through a learning healthcare system.

Large language models have been increasing in size due to their success in a wide range of applications. This calls for a pressing need to reduce memory usage to make them more accessible. Post-training quantization is a popular technique which uses fewer bits (e.g., 4--8 bits) to represent the model without retraining it. However, it remains a challenging task to perform quantization in an ultra-low-bit setup (e.g., 2 bits). In this paper, we propose InvarExplore, a unified framework that systematically explores different model invariance at the same time, allowing us to take advantage of the synergy between each type of invariance. Importantly, InvarExplore features a discrete search algorithm that enables us to explore permutation invariance, which is under-studied as it cannot be optimized with gradient-based methods. Results show that InvarExplore is compatible with existing state-of-the-art methods, achieving an add-on performance improvement over strong competing methods.

We propose Heterogeneous Swarms, an algorithm to design multi-LLM systems by jointly optimizing model roles and weights. We represent multi-LLM systems as directed acyclic graphs (DAGs) of LLMs with topological message passing for collaborative generation. Given a pool of LLM experts and a utility function, Heterogeneous Swarms employs two iterative steps: role-step and weight-step. For role-step, we interpret model roles as learning a DAG that specifies the flow of inputs and outputs between LLMs. Starting from a swarm of random continuous adjacency matrices, we decode them into discrete DAGs, call the LLMs in topological order, evaluate on the utility function (e.g. accuracy on a task), and optimize the adjacency matrices with particle swarm optimization based on the utility score. For weight-step, we assess the contribution of individual LLMs in the multi-LLM systems and optimize model weights with swarm intelligence. We propose JFK-score to quantify the individual contribution of each LLM in the best-found DAG of the role-step, then optimize model weights with particle swarm optimization based on the JFK-score. Experiments demonstrate that Heterogeneous Swarms outperforms 15 role- and/or weight-based baselines by 18.5% on average across 12 tasks. Further analysis reveals that Heterogeneous Swarms discovers multi-LLM systems with heterogeneous model roles and substantial collaborative gains, and benefits from the diversity of language models.