We address the question of how to successively add new knowledge to an LLM whilst retaining previously-added knowledge. We consider two settings, semi-cooperative and fully-cooperative. Overall, LoRA performs better in most cases than full-fine tuning of all parameters when both new knowledge acquisition and retention of old, including recent, knowledge are taken into account. In the semi-cooperative setting, where datasets are not available after training, MOE mixing, model merging, and LoRA-based orthogonal subspace sequential learning, using a small weight on the orthogonality term, perform well. In the fully-cooperative setting where datasets remain available, joint training and sequential training with replay are both effective approaches with LoRA training generally preferable to full fine-tuning. The codes needed to reproduce the results are provided in an open source repository.

Recently, research on Text-Attributed Graphs (TAGs) has gained significant attention due to the prevalence of free-text node features in real-world applications and the advancements in Large Language Models (LLMs) that bolster TAG methodologies. However, current TAG approaches face two primary challenges: (i) Heavy reliance on label information and (ii) Limited cross-domain zero/few-shot transferability. These issues constrain the scaling of both data and model size, owing to high labor costs and scaling laws, complicating the development of graph foundation models with strong transferability. In this work, we propose the GraphCLIP framework to address these challenges by learning graph foundation models with strong cross-domain zero/few-shot transferability through a self-supervised contrastive graph-summary pretraining method. Specifically, we generate and curate large-scale graph-summary pair data with the assistance of LLMs, and introduce a novel graph-summary pretraining method, combined with invariant learning, to enhance graph foundation models with strong cross-domain zero-shot transferability. For few-shot learning, we propose a novel graph prompt tuning technique aligned with our pretraining objective to mitigate catastrophic forgetting and minimize learning costs. Extensive experiments show the superiority of GraphCLIP in both zero-shot and few-shot settings, while evaluations across various downstream tasks confirm the versatility of GraphCLIP. Our code is available at: https://github.com/ZhuYun97/GraphCLIP

What will information entry look like in the next generation of digital products? Since the 1970s, user access to relevant information has relied on domain-specific architectures of information retrieval (IR). Over the past two decades, the advent of modern IR systems, including web search engines and personalized recommender systems, has greatly improved the efficiency of retrieving relevant information from vast data corpora. However, the core paradigm of these IR systems remains largely unchanged, relying on filtering a predefined set of candidate items. Since 2022, breakthroughs in large language models (LLMs) have begun transforming how information is accessed, establishing a new technical paradigm. In this position paper, we introduce Agentic Information Retrieval (Agentic IR), a novel IR paradigm shaped by the capabilities of LLM agents. Agentic IR expands the scope of accessible tasks and leverages a suite of new techniques to redefine information retrieval. We discuss three types of cutting-edge applications of agentic IR and the challenges faced. We propose that agentic IR holds promise for generating innovative applications, potentially becoming a central information entry point in future digital ecosystems.

Hallucinations in Large Language Models (LLMs) remain a major obstacle, particularly in high-stakes applications where factual accuracy is critical. While representation editing and reading methods have made strides in reducing hallucinations, their heavy reliance on specialised tools and training on in-domain samples, makes them difficult to scale and prone to overfitting. This limits their accuracy gains and generalizability to diverse datasets. This paper presents a lightweight method, Norm Voting (NoVo), which harnesses the untapped potential of attention head norms to dramatically enhance factual accuracy in zero-shot multiple-choice questions (MCQs). NoVo begins by automatically selecting truth-correlated head norms with an efficient, inference-only algorithm using only 30 random samples, allowing NoVo to effortlessly scale to diverse datasets. Afterwards, selected head norms are employed in a simple voting algorithm, which yields significant gains in prediction accuracy. NoVo demonstrates exceptional generalization to 20 diverse datasets, with significant gains in over 90% of them, far exceeding all current representation editing and reading methods. NoVo also reveals promising gains to finetuning strategies and building textual adversarial defence. NoVo's effectiveness with head norms opens new frontiers in LLM interpretability, robustness and reliability. One of the most significant challenges facing Large Language Models (LLMs) today is their tendency to hallucinate--outputs that are factually incorrect or entirely fabricated (Zhang et al., 2023b). This flaw is particularly serious in high-stakes applications like finance and healthcare, where even small errors can lead to huge losses and compromised patient safety (Kang & Liu, 2023; Pal et al., 2023). Reducing factual hallucinations is a critical research area with major practical benefits, essential for realising the full potential of LLMs to revolutionise these industries by enhancing efficiency and decision-making, and safeguarding against costly and harmful errors (Kaddour et al., 2023). Given these serious risks and the high cost of retraining LLMs, it is crucial to find affordable techniques to reduce factual hallucinations. Although inference techniques such as retrieval augmentation and prompt engineering work well, they come with significant limitations: latency and external dependencies, and the need for user expertise, respectively (Zhao et al., 2024; Sahoo et al., 2024). In response, we turn to representation editing and reading methods (REAR) (Zou et al., 2023), which operate within the model, ensuring rapid response times and eliminating the need for external data or user interaction.

Resolving knowledge conflicts is a crucial challenge in Question Answering (QA) tasks, as the internet contains numerous conflicting facts and opinions. While some research has made progress in tackling ambiguous settings where multiple valid answers exist, these approaches often neglect to provide source citations, leaving users to evaluate the factuality of each answer. On the other hand, existing work on citation generation has focused on unambiguous settings with single answers, failing to address the complexity of real-world scenarios. Despite the importance of both aspects, no prior research has combined them, leaving a significant gap in the development of QA systems. In this work, we bridge this gap by proposing the novel task of QA with source citation in ambiguous settings, where multiple valid answers exist. To facilitate research in this area, we create a comprehensive framework consisting of: (1) five novel datasets, obtained by augmenting three existing reading comprehension datasets with citation meta-data across various ambiguous settings, such as distractors and paraphrasing; (2) the first ambiguous multi-hop QA dataset featuring real-world, naturally occurring contexts; (3) two new metrics to evaluate models' performances; and (4) several strong baselines using rule-based, prompting, and finetuning approaches over five large language models. We hope that this new task, datasets, metrics, and baselines will inspire the community to push the boundaries of QA research and develop more trustworthy and interpretable systems.

GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language Models to perceive and generate images, texts, and speeches end-to-end with publicly available data remains challenging in the open-source community. Existing vision-language models rely on external tools for the speech processing, while speech-language models still suffer from limited or even without vision-understanding abilities. To address this gap, we propose EMOVA (EMotionally Omni-present Voice Assistant), to enable Large Language Models with end-to-end speech capabilities while maintaining the leading vision-language performance. With a semantic-acoustic disentangled speech tokenizer, we notice surprisingly that omni-modal alignment can further enhance vision-language and speech abilities compared with the corresponding bi-modal aligned counterparts. Moreover, a lightweight style module is proposed for flexible speech style controls (e.g., emotions and pitches). For the first time, EMOVA achieves state-of-the-art performance on both the vision-language and speech benchmarks, and meanwhile, supporting omni-modal spoken dialogue with vivid emotions.

The rocketing prosperity of large language models (LLMs) in recent years has boosted the prevalence of vision-language models (VLMs) in the medical sector. In our online medical consultation scenario, a doctor responds to the texts and images provided by a patient in multiple rounds to diagnose her/his health condition, forming a multi-turn multimodal medical dialogue format. Unlike high-quality images captured by professional equipment in traditional medical visual question answering (Med-VQA), the images in our case are taken by patients' mobile phones. These images have poor quality control, with issues such as excessive background elements and the lesion area being significantly off-center, leading to degradation of vision-language alignment in the model training phase. In this paper, we propose ZALM3, a Zero-shot strategy to improve vision-language ALignment in Multi-turn Multimodal Medical dialogue. Since we observe that the preceding text conversations before an image can infer the regions of interest (RoIs) in the image, ZALM3 employs an LLM to summarize the keywords from the preceding context and a visual grounding model to extract the RoIs. The updated images eliminate unnecessary background noise and provide more effective vision-language alignment. To better evaluate our proposed method, we design a new subjective assessment metric for multi-turn unimodal/multimodal medical dialogue to provide a fine-grained performance comparison. Our experiments across three different clinical departments remarkably demonstrate the efficacy of ZALM3 with statistical significance.

Integrating structured knowledge from tabular formats poses significant challenges within natural language processing (NLP), mainly when dealing with complex, semi-structured tables like those found in the FeTaQA dataset. These tables require advanced methods to interpret and generate meaningful responses accurately. Traditional approaches, such as SQL and SPARQL, often fail to fully capture the semantics of such data, especially in the presence of irregular table structures like web tables. This paper addresses these challenges by proposing a novel approach that extracts triples straightforward from tabular data and integrates it with a retrieval-augmented generation (RAG) model to enhance the accuracy, coherence, and contextual richness of responses generated by a fine-tuned GPT-3.5-turbo-0125 model. Our approach significantly outperforms existing baselines on the FeTaQA dataset, particularly excelling in Sacre-BLEU and ROUGE metrics. It effectively generates contextually accurate and detailed long-form answers from tables, showcasing its strength in complex data interpretation.

Linguistically inclusive LLMs -- which maintain good performance regardless of the language with which they are prompted -- are necessary for the diffusion of AI benefits around the world. Multilingual jailbreaks that rely on language translation to evade safety measures undermine the safe and inclusive deployment of AI systems. We provide policy recommendations to enhance the multilingual capabilities of AI while mitigating the risks of multilingual jailbreaks. We examine how a language's level of resourcing relates to how vulnerable LLMs are to multilingual jailbreaks in that language. We do this by testing five advanced AI models across 24 official languages of the EU. Building on prior research, we propose policy actions that align with the EU legal landscape and institutional framework to address multilingual jailbreaks, while promoting linguistic inclusivity. These include mandatory assessments of multilingual capabilities and vulnerabilities, public opinion research, and state support for multilingual AI development. The measures aim to improve AI safety and functionality through EU policy initiatives, guiding the implementation of the EU AI Act and informing regulatory efforts of the European AI Office.

Performance and Power: Systematic Evaluation of AI Workloads on Accelerators with CARAML Chelsea Maria John, Stepan Nassyr, Carolin Penke, Andreas Herten J ulich Supercomputing Centre F orschungszentrum J ulich J ulich, Germany Abstract --The rapid advancement of machine learning (ML) technologies has driven the development of specialized hardware accelerators designed to facilitate more efficient model training. This paper introduces the CARAML benchmark suite, which is employed to assess performance and energy consumption during the training of transformer-based large language models and computer vision models on a range of hardware accelerators, including systems from NVIDIA, AMD, and Graphcore. CARAML provides a compact, automated, extensible, and reproducible framework for assessing the performance and energy of ML workloads across various novel hardware architectures. The design and implementation of CARAML, along with a custom power measurement tool called jpwr, are discussed in detail. I NTRODUCTION Fueled by the growing interest in training ever larger deep neural networks, such as large language models and other foundation models, the demands for hardware specialized on these workloads have grown immensely. Graphics processing units (GPUs) have evolved from their origins in computer graphics to become the primary computational engines of the AI revolution. While the central processing unit (CPU) controls a program's execution flow, it offloads compute-intensive highly-parallel tasks to the GPU (the accelerator). Evolving from a pioneering company, NVIDIA has emerged as the dominant player in the market as of 2024, spearheading current hardware developments. Other vendors, such as AMD and Intel, also provide GPUs aiming to accelerate model training and inference. Another promising class of AI accelerators is based on the idea of distributed local per-compute-unit memory together with on-chip message passing, in contrast to a shared memory hierarchy, typical to classical CPUs and GPUs. Performance characteristics not only vary between generations and vendors, but depend on the node or cluster configuration in which the accelerator is embedded, including CPU, memory, and interconnect. When evaluating and comparing these heterogeneous hardware options, e.g. for purchase decisions in an academic or industrial setting, it is not sufficient to compare hardware characteristics such as number of cores, thermal design power (TDP), theoretic bandwidth, or peak performance in F LO P/s . Their effect on workload performance is not straightforward, and the accelerator architectures might barely be comparable. Performance data reflecting the actual intended workloads, collected on various competing systems independently of vendor interests, offer highly valuable information. Power consumption is one such important metric in this regard.