Foundation Models (FMs) display exceptional performance in tasks such as natural language processing and are being applied across a growing range of disciplines. Although typically trained on large public datasets, FMs are often fine-tuned or integrated into Retrieval-Augmented Generation (RAG) systems, which rely on private data. This access, along with their size and costly training, heightens the risk of intellectual property theft. Moreover, multimodal FMs may expose sensitive information. In this work, we examine the FM threat model and discuss the practicality and comprehensiveness of various approaches for securing against them, such as ML-based methods and trusted execution environments (TEEs). We demonstrate that TEEs offer an effective balance between strong security properties, usability, and performance. Specifically, we present a solution achieving less than 10\% overhead versus bare metal for the full Llama2 7B and 13B inference pipelines running inside \intel\ SGX and \intel\ TDX. We also share our configuration files and insights from our implementation. To our knowledge, our work is the first to show the practicality of TEEs for securing FMs.

A vast amount of textual data is added to the internet daily, making utilization and interpretation of such data difficult and cumbersome. As a result, automatic text summarization is crucial for extracting relevant information, saving precious reading time. Although many transformer-based models excel in summarization, they are constrained by their input size, preventing them from processing texts longer than their context size. This study introduces three novel algorithms that allow any LLM to efficiently overcome its input size limitation, effectively utilizing its full potential without any architectural modifications. We test our algorithms on texts with more than 70,000 words, and our experiments show a significant increase in BERTScore with competitive ROUGE scores.

Universities are increasingly adopting data-driven strategies to enhance student success, with AI applications like Learning Analytics (LA) and Predictive Learning Analytics (PLA) playing a key role in identifying at-risk students, personalising learning, supporting teachers, and guiding educational decision-making. However, concerns are rising about potential harms these systems may pose, such as algorithmic biases leading to unequal support for minority students. While many have explored the need for Responsible AI in LA, existing works often lack practical guidance for how institutions can operationalise these principles. In this paper, we propose a novel Responsible AI framework tailored specifically to LA in Higher Education (HE). We started by mapping 11 established Responsible AI frameworks, including those by leading tech companies, to the context of LA in HE. This led to the identification of seven key principles such as transparency, fairness, and accountability. We then conducted a systematic review of the literature to understand how these principles have been applied in practice. Drawing from these findings, we present a novel framework that offers practical guidance to HE institutions and is designed to evolve with community input, ensuring its relevance as LA systems continue to develop.

In sensitive domains, such as legal or medial domains, the correctness of information given to users is critical. To address this, the recently introduced task Conversational Tree Search (CTS) provides a graph-based framework for controllable task-oriented dialog in sensitive domains. However, a big drawback of state-of-the-art CTS agents is their long training time, which is especially problematic as a new agent must be trained every time the associated domain graph is updated. The goal of this paper is to eliminate the need for training CTS agents altogether. To achieve this, we implement a novel LLM-based method for zero-shot, controllable CTS agents. We show that these agents significantly outperform state-of-the-art CTS agents (p<0.0001; Barnard Exact test) in simulation. This generalizes to all available CTS domains. Finally, we perform user evaluation to test the agent performance in the wild, showing that our policy significantly (p<0.05; Barnard Exact) improves task-success compared to the state-of-the-art Reinforcement Learning-based CTS agent.

The success of modern Machine Learning (ML) systems depends on the quality and quantity of data used for training, which directly influences model performance and generalization capabilities. To this aim, high-quality, diverse, and representative datasets are essential for accurate and unbiased predictions. For instance, insufficient or biased data can lead to poor model performance, inaccuracies, and unintended consequences. Ethical and legal aspects are critical, too.

Unlike regular models, these very simple models--often referred to as toy models--are not required to be linked to the real world through structural similarity or resemblance relations. They are not meant to be approximations of the target world system, and in some cases, they are not even required to be representational. In semantic terms, they do not accurately map onto their targets. Despite these limitations, they are still useful in understanding theoretical concepts and possible configurations of the target system. Paradigmatic examples of toy models include Boyle's law and the Ising model in physics, the Lotka-Volterra model in population ecology, and the Schelling model in the social sciences (Weisberg, 2013). In recent years, philosophers of science have become interested in toy models (Grüne-Yanoff, 2009; Luczak, 2017; Reutlinger et al., 2018; Frigg & Nguyen, 2017; Nguyen, 2020). The main purpose of this literature is to explore the nature of these models and examine how they perform their epistemic function. Despite lacking the regular descriptive and predictive features of full-scale scientific models, they often offer an elementary understanding of a phenomenon. Their definitions of "toy model" differ as well as their assessment of the importance of representation in modelling generally, but they all agree that toy models play an important epistemic role in scientific research, exploration, and pedagogy.

To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized finetuning, and more. Despite the development, it is nontrivial to reach a principled understanding of fairness and an effective algorithm that can consistently debias language models. In this work, by rigorous evaluations of Neural Collapse - a learning phenomenon happen in last-layer representations and classifiers in deep networks - on fairness-related words, we find that debiased language models exhibit collapsed alignment between token representations and word embeddings. More importantly, this observation inspires us to design a principled fine-tuning method that can effectively improve fairness in a wide range of debiasing methods, while still preserving the performance of language models on standard natural language understanding tasks. The rise of pre-trained language models (PLMs) has revolutionized natural language processing, greatly enhancing tasks like reasoning and prediction by harnessing the semantic richness of language data. Despite their effectiveness, these models, trained on extensive corpora, often reflect and even intensify societal biases in their training datasets. Such biases manifest in the association of demographic groups with specific roles or capabilities, affecting fairness in applications ranging from legal analytics to hiring processes [49; 12; 38; 2; 52; 3; 7]. Thus, it is crucial to address and mitigate these biases to prevent discriminatory practices in downstream applications [70; 64; 46].

In social dilemmas where the collective and self-interests are at odds, people typically cooperate less with machines than with fellow humans, a phenomenon termed the machine penalty. Overcoming this penalty is critical for successful human-machine collectives, yet current solutions often involve ethically-questionable tactics, like concealing machines' non-human nature. In this study, with 1,152 participants, we explore the possibility of closing this research question by using Large Language Models (LLMs), in scenarios where communication is possible between interacting parties. We design three types of LLMs: (i) Cooperative, aiming to assist its human associate; (ii) Selfish, focusing solely on maximizing its self-interest; and (iii) Fair, balancing its own and collective interest, while slightly prioritizing self-interest. Our findings reveal that, when interacting with humans, fair LLMs are able to induce cooperation levels comparable to those observed in human-human interactions, even when their non-human nature is fully disclosed. In contrast, selfish and cooperative LLMs fail to achieve this goal. Post-experiment analysis shows that all three types of LLMs succeed in forming mutual cooperation agreements with humans, yet only fair LLMs, which occasionally break their promises, are capable of instilling a perception among humans that cooperating with them is the social norm, and eliciting positive views on their trustworthiness, mindfulness, intelligence, and communication quality. Our findings suggest that for effective human-machine cooperation, bot manufacturers should avoid designing machines with mere rational decision-making or a sole focus on assisting humans. Instead, they should design machines capable of judiciously balancing their own interest and the interest of humans.

Large Language Models (LLMs) have excelled in various tasks but are still vulnerable to jailbreaking attacks, where attackers create jailbreak prompts to mislead the model to produce harmful or offensive content. Current jailbreak methods either rely heavily on manually crafted templates, which pose challenges in scalability and adaptability, or struggle to generate semantically coherent prompts, making them easy to detect. Additionally, most existing approaches involve lengthy prompts, leading to higher query costs.In this paper, to remedy these challenges, we introduce a novel jailbreaking attack framework, which is an automated, black-box jailbreaking attack framework that adapts the black-box fuzz testing approach with a series of customized designs. Instead of relying on manually crafted templates, our method starts with an empty seed pool, removing the need to search for any related jailbreaking templates. We also develop three novel question-dependent mutation strategies using an LLM helper to generate prompts that maintain semantic coherence while significantly reducing their length. Additionally, we implement a two-level judge module to accurately detect genuine successful jailbreaks. We evaluated our method on 7 representative LLMs and compared it with 5 state-of-the-art jailbreaking attack strategies. For proprietary LLM APIs, such as GPT-3.5 turbo, GPT-4, and Gemini-Pro, our method achieves attack success rates of over 90%,80% and 74%, respectively, exceeding existing baselines by more than 60%. Additionally, our method can maintain high semantic coherence while significantly reducing the length of jailbreak prompts. When targeting GPT-4, our method can achieve over 78% attack success rate even with 100 tokens. Moreover, our method demonstrates transferability and is robust to state-of-the-art defenses. We will open-source our codes upon publication.

Discrete diffusion has achieved state-of-the-art performance, outperforming or approaching autoregressive models on standard benchmarks. In this work, we introduce Discrete Diffusion with Planned Denoising (DDPD), a novel framework that separates the generation process into two models: a planner and a denoiser. At inference time, the planner selects which positions to denoise next by identifying the most corrupted positions in need of denoising, including both initially corrupted and those requiring additional refinement. This plan-and-denoise approach enables more efficient reconstruction during generation by iteratively identifying and denoising corruptions in the optimal order. DDPD outperforms traditional denoiser-only mask diffusion methods, achieving superior results on language modeling benchmarks such as text8, OpenWebText, and token-based generation on ImageNet $256 \times 256$. Notably, in language modeling, DDPD significantly reduces the performance gap between diffusion-based and autoregressive methods in terms of generative perplexity. Code is available at https://github.com/liusulin/DDPD.