Conventional fair graph clustering methods face two primary challenges: i) They prioritize balanced clusters at the expense of cluster cohesion by imposing rigid constraints, ii) Existing methods of both individual and group-level fairness in graph partitioning mostly rely on eigen decompositions and thus, generally lack interpretability. To address these issues, we propose iFairNMTF, an individual Fairness Nonnegative Matrix Tri-Factorization model with contrastive fairness regularization that achieves balanced and cohesive clusters. By introducing fairness regularization, our model allows for customizable accuracy-fairness trade-offs, thereby enhancing user autonomy without compromising the interpretability provided by nonnegative matrix tri-factorization. Experimental evaluations on real and synthetic datasets demonstrate the superior flexibility of iFairNMTF in achieving fairness and clustering performance.

The reasoning capabilities of LLMs are currently hotly debated. We examine the issue from the perspective of claim/rumour verification. We propose the first logical reasoning framework designed to break down any claim or rumor paired with evidence into the atomic reasoning steps necessary for verification. Based on our framework, we curate two annotated collections of such claim/evidence pairs: a synthetic dataset from Wikipedia and a real-world set stemming from rumours circulating on Twitter. We use them to evaluate the reasoning capabilities of GPT-3.5-Turbo and GPT-4 (hereinafter referred to as ChatGPT) within the context of our framework, providing a thorough analysis. Our results show that ChatGPT struggles in abductive reasoning, although this can be somewhat mitigated by using manual Chain of Thought (CoT) as opposed to Zero Shot (ZS) and ZS CoT approaches. Our study contributes to the growing body of research suggesting that ChatGPT's reasoning processes are unlikely to mirror human-like reasoning, and that LLMs need to be more rigorously evaluated in order to distinguish between hype and actual capabilities, especially in high stake real-world tasks such as claim verification.

With the advent of large language models (LLM), the line between human-crafted and machine-generated texts has become increasingly blurred. This paper delves into the inquiry of identifying discernible and unique linguistic properties in texts that were written by humans, particularly uncovering the underlying discourse structures of texts beyond their surface structures. Introducing a novel methodology, we leverage hierarchical parse trees and recursive hypergraphs to unveil distinctive discourse patterns in texts produced by both LLMs and humans. Empirical findings demonstrate that, although both LLMs and humans generate distinct discourse patterns influenced by specific domains, human-written texts exhibit more structural variability, reflecting the nuanced nature of human writing in different domains. Notably, incorporating hierarchical discourse features enhances binary classifiers' overall performance in distinguishing between human-written and machine-generated texts, even on out-of-distribution and paraphrased samples. This underscores the significance of incorporating hierarchical discourse features in the analysis of text patterns. The code and dataset will be available at [TBA].

The increasing depth of parametric domain knowledge in large language models (LLMs) is fueling their rapid deployment in real-world applications. In high-stakes and knowledge-intensive tasks, understanding model vulnerabilities is essential for quantifying the trustworthiness of model predictions and regulating their use. The recent discovery of named entities as adversarial examples in natural language processing tasks raises questions about their potential guises in other settings. Here, we propose a powerscaled distance-weighted sampling scheme in embedding space to discover diverse adversarial entities as distractors. We demonstrate its advantage over random sampling in adversarial question answering on biomedical topics. Our approach enables the exploration of different regions on the attack surface, which reveals two regimes of adversarial entities that markedly differ in their characteristics. Moreover, we show that the attacks successfully manipulate token-wise Shapley value explanations, which become deceptive in the adversarial setting. Our investigations illustrate the brittleness of domain knowledge in LLMs and reveal a shortcoming of standard evaluations for high-capacity models.

Self-distillation (SD) is the process of training a student model using the outputs of a teacher model, with both models sharing the same architecture. Our study theoretically examines SD in multi-class classification with cross-entropy loss, exploring both multi-round SD and SD with refined teacher outputs, inspired by partial label learning (PLL). By deriving a closed-form solution for the student model's outputs, we discover that SD essentially functions as label averaging among instances with high feature correlations. Initially beneficial, this averaging helps the model focus on feature clusters correlated with a given instance for predicting the label. However, it leads to diminishing performance with increasing distillation rounds. Additionally, we demonstrate SD's effectiveness in label noise scenarios and identify the label corruption condition and minimum number of distillation rounds needed to achieve 100% classification accuracy. Our study also reveals that one-step distillation with refined teacher outputs surpasses the efficacy of multi-step SD using the teacher's direct output in high noise rate regimes.

Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models with human values, reward hacking, also termed reward overoptimization, remains a critical challenge, which primarily stems from limitations in reward modeling, i.e., generalizability of the reward model and inconsistency in the preference dataset. In this work, we tackle this problem from an information theoretic-perspective, and propose a generalizable and robust framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective to filter out irrelevant information and developing a mechanism for model complexity modulation. Notably, we further identify a correlation between overoptimization and outliers in the latent space, establishing InfoRM as a promising tool for detecting reward overoptimization. Inspired by this finding, we propose the Integrated Cluster Deviation Score (ICDS), which quantifies deviations in the latent space, as an indicator of reward overoptimization to facilitate the development of online mitigation strategies. Extensive experiments on a wide range of settings and model scales (70M, 440M, 1.4B, and 7B) support the effectiveness of InfoRM. Further analyses reveal that InfoRM's overoptimization detection mechanism is effective, potentially signifying a notable advancement in the field of RLHF. Code will be released upon acceptance.

We already know that OpenAI's chatbots can pass the bar exam without going to law school. Now, just in time for the Oscars, a new OpenAI app called Sora hopes to master cinema without going to film school. For now a research product, Sora is going out to a few select creators and a number of security experts who will red-team it for safety vulnerabilities. OpenAI plans to make it available to all wannabe auteurs at some unspecified date, but it decided to preview it in advance. Other companies, from giants like Google to startups like Runway, have already revealed text-to-video AI projects.

The parents of a teenager who was killed in Florida's Parkland school shooting in 2018 have started a bold new project called The Shotline to lobby for stricter gun laws in the country. The Shotline uses AI to recreate the voices of children killed by gun violence and send recordings through automated calls to lawmakers, The Wall Street Journal reported. The project launched on Wednesday, six years after a gunman killed 17 people and injured more than a dozen at a high school in Parkland, Florida. It features the voice of six children, some as young as ten, and young adults, who have lost their lives in incidents of gun violence across the US. Once you type in your zip code, The Shotline finds your local representative and lets you place an automated call from one of the six dead people in their own voice, urging for stronger gun control laws.

Selecting high-quality pre-training data is important for creating capable language models, but existing methods rely on simple heuristics. We introduce QuRating, a method for selecting pre-training data that captures the abstract qualities of texts which humans intuitively perceive. In this paper, we investigate four qualities - writing style, required expertise, facts & trivia, and educational value. We find that LLMs are able to discern these qualities and observe that they are better at making pairwise judgments of texts than at rating the quality of a text directly. We train a QuRater model to learn scalar ratings from pairwise judgments, and use it to annotate a 260B training corpus with quality ratings for each of the four criteria. In our experiments, we select 30B tokens according to the different quality ratings and train 1.3B-parameter language models on the selected data. We find that it is important to balance quality and diversity, as selecting only the highest-rated documents leads to poor results. When we sample using quality ratings as logits over documents, our models achieve lower perplexity and stronger in-context learning performance than baselines. Beyond data selection, we use the quality ratings to construct a training curriculum which improves performance without changing the training dataset. We extensively analyze the quality ratings and discuss their characteristics, biases, and wider implications.

The report describes the discussions from the Workshop on Mathematical Opportunities in Digital Twins (MATH-DT) from December 11-13, 2023, George Mason University. It illustrates that foundational Mathematical advances are required for Digital Twins (DTs) that are different from traditional approaches. A traditional model, in biology, physics, engineering or medicine, starts with a generic physical law (e.g., equations) and is often a simplification of reality. A DT starts with a specific ecosystem, object or person (e.g., personalized care) representing reality, requiring multi -scale, -physics modeling and coupling. Thus, these processes begin at opposite ends of the simulation and modeling pipeline, requiring different reliability criteria and uncertainty assessments. Additionally, unlike existing approaches, a DT assists humans to make decisions for the physical system, which (via sensors) in turn feeds data into the DT, and operates for the life of the physical system. While some of the foundational mathematical research can be done without a specific application context, one must also keep specific applications in mind for DTs. E.g., modeling a bridge or a biological system (a patient), or a socio-technical system (a city) is very different. The models range from differential equations (deterministic/uncertain) in engineering, to stochastic in biology, including agent-based. These are multi-scale hybrid models or large scale (multi-objective) optimization problems under uncertainty. There are no universal models or approaches. For e.g., Kalman filters for forecasting might work in engineering, but can fail in biomedical domain. Ad hoc studies, with limited systematic work, have shown that AI/ML methods can fail for simple engineering systems and can work well for biomedical problems. A list of `Mathematical Opportunities and Challenges' concludes the report.