Devindra: because like you could just always just take a photo of something and be like, yeah, that's how we wonder if it's going to Cherlynn: be a ram hog.

Donald Trump and Joe Biden discussed their metal agility and sporting prowess during an often heated presidential debate.

Aligning language models (LMs) to human preferences has emerged as a critical pursuit, enabling these models to better serve diverse user needs. Existing methods primarily focus on optimizing LMs for a single reward function, limiting their adaptability to varied objectives. Here, we propose $\textbf{multi-objective decoding (MOD)}$, a decoding-time algorithm that outputs the next token from a linear combination of predictions of all base models, for any given weightings over different objectives. We exploit a common form among a family of $f$-divergence regularized alignment approaches (such as PPO, DPO, and their variants) to identify a closed-form solution by Legendre transform, and derive an efficient decoding strategy. Theoretically, we show why existing approaches can be sub-optimal even in natural settings and obtain optimality guarantees for our method. Empirical results demonstrate the effectiveness of the algorithm. For example, compared to a parameter-merging baseline, MOD achieves 12.8% overall reward improvement when equally optimizing towards $3$ objectives. Moreover, we experiment with MOD on combining three fully-finetuned LLMs of different model sizes, each aimed at different objectives such as safety, coding, and general user preference. Unlike traditional methods that require careful curation of a mixture of datasets to achieve comprehensive improvement, we can quickly experiment with preference weightings using MOD to find the best combination of models. Our best combination reduces toxicity on Toxigen to nearly 0% and achieves 7.9--33.3% improvement across other three metrics ($\textit{i.e.}$, Codex@1, GSM-COT, BBH-COT).

Enhancing the sparsity of data-driven reduced-order models (ROMs) has gained increasing attention in recent years. In this work, we analyze an efficient approach to identifying skillful ROMs with a sparse structure using an information-theoretic indicator called causation entropy. The causation entropy quantifies in a statistical way the additional contribution of each term to the underlying dynamics beyond the information already captured by all the other terms in the ansatz. By doing so, the causation entropy assesses the importance of each term to the dynamics before a parameter estimation procedure is performed. Thus, the approach can be utilized to eliminate terms with little dynamic impact, leading to a parsimonious structure that retains the essential physics. To circumvent the difficulty of estimating high-dimensional probability density functions (PDFs) involved in the causation entropy computation, we leverage Gaussian approximations for such PDFs, which are demonstrated to be sufficient even in the presence of highly non-Gaussian dynamics. The effectiveness of the approach is illustrated by the Kuramoto-Sivashinsky equation by building sparse causation-based ROMs for various purposes, such as recovering long-term statistics and inferring unobserved dynamics via data assimilation with partial observations.

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning interfaces, we introduce covert malicious finetuning, a method to compromise model safety via finetuning while evading detection. Our method constructs a malicious dataset where every individual datapoint appears innocuous, but finetuning on the dataset teaches the model to respond to encoded harmful requests with encoded harmful responses. Applied to GPT-4, our method produces a finetuned model that acts on harmful instructions 99% of the time and avoids detection by defense mechanisms such as dataset inspection, safety evaluations, and input/output classifiers. Our findings question whether black-box finetuning access can be secured against sophisticated adversaries.

Large language models (LLMs) have gained significant attention due to their ability to mimic human language. Identifying texts generated by LLMs is crucial for understanding their capabilities and mitigating potential consequences. This paper analyzes datasets of varying text lengths: small, medium, and large. We compare the performance of machine learning algorithms on four datasets: (1) small (tweets from Election, FIFA, and Game of Thrones), (2) medium (Wikipedia introductions and PubMed abstracts), and (3) large (OpenAI web text dataset). Our results indicate that LLMs with very large parameters (such as the XL-1542 variant of GPT2 with 1542 million parameters) were harder (74%) to detect using traditional machine learning methods. However, detecting texts of varying lengths from LLMs with smaller parameters (762 million or less) can be done with high accuracy (96% and above). We examine the characteristics of human and machine-generated texts across multiple dimensions, including linguistics, personality, sentiment, bias, and morality. Our findings indicate that machine-generated texts generally have higher readability and closely mimic human moral judgments but differ in personality traits. SVM and Voting Classifier (VC) models consistently achieve high performance across most datasets, while Decision Tree (DT) models show the lowest performance. Model performance drops when dealing with rephrased texts, particularly shorter texts like tweets. This study underscores the challenges and importance of detecting LLM-generated texts and suggests directions for future research to improve detection methods and understand the nuanced capabilities of LLMs.

Enterprises have a growing need to identify relevant tables in data lakes; e.g. tables that are unionable, joinable, or subsets of each other. Tabular neural models can be helpful for such data discovery tasks. In this paper, we present TabSketchFM, a neural tabular model for data discovery over data lakes. First, we propose a novel pre-training sketch-based approach to enhance the effectiveness of data discovery techniques in neural tabular models. Second, to further finetune the pretrained model for several downstream tasks, we develop LakeBench, a collection of 8 benchmarks to help with different data discovery tasks such as finding tasks that are unionable, joinable, or subsets of each other. We then show on these finetuning tasks that TabSketchFM achieves state-of-the art performance compared to existing neural models. Third, we use these finetuned models to search for tables that are unionable, joinable, or can be subsets of each other. Our results demonstrate improvements in F1 scores for search compared to state-of-the-art techniques (even up to 70% improvement in a joinable search benchmark). Finally, we show significant transfer across datasets and tasks establishing that our model can generalize across different tasks over different data lakes

Traditional keyphrase prediction methods predict a single set of keyphrases per document, failing to cater to the diverse needs of users and downstream applications. To bridge the gap, we introduce on-demand keyphrase generation, a novel paradigm that requires keyphrases that conform to specific high-level goals or intents. For this task, we present MetaKP, a large-scale benchmark comprising four datasets, 7500 documents, and 3760 goals across news and biomedical domains with human-annotated keyphrases. Leveraging MetaKP, we design both supervised and unsupervised methods, including a multi-task fine-tuning approach and a self-consistency prompting method with large language models. The results highlight the challenges of supervised fine-tuning, whose performance is not robust to distribution shifts. By contrast, the proposed self-consistency prompting approach greatly improves the performance of large language models, enabling GPT-4o to achieve 0.548 SemF1, surpassing the performance of a fully fine-tuned BART-base model. Finally, we demonstrate the potential of our method to serve as a general NLP infrastructure, exemplified by its application in epidemic event detection from social media.

Entanglement is a key resource for a wide range of tasks in quantum information and computing. Thus, verifying availability of this quantum resource is essential. Extensive research on entanglement detection has led to no-go theorems (Lu et al. [Phys. Rev. Lett., 116, 230501 (2016)]) that highlight the need for full state tomography (FST) in the absence of adaptive or joint measurements. Recent advancements, as proposed by Zhu, Teo, and Englert [Phys. Rev. A, 81, 052339, 2010], introduce a single-parameter family of entanglement witness measurements which are capable of conclusively detecting certain entangled states and only resort to FST when all witness measurements are inconclusive. We find a variety of realistic noisy two-qubit quantum states $\mathcal{F}$ that yield conclusive results under this witness family. We solve the problem of detecting entanglement among $K$ quantum states in $\mathcal{F}$, of which $m$ states are entangled, with $m$ potentially unknown. We recognize a structural connection of this problem to the Bad Arm Identification problem in stochastic Multi-Armed Bandits (MAB). In contrast to existing quantum bandit frameworks, we establish a new correspondence tailored for entanglement detection and term it the $(m,K)$-quantum Multi-Armed Bandit. We implement two well-known MAB policies for arbitrary states derived from $\mathcal{F}$, present theoretical guarantees on the measurement/sample complexity and demonstrate the practicality of the policies through numerical simulations. More broadly, this paper highlights the potential for employing classical machine learning techniques for quantum entanglement detection.

This paper explores the critical issue of enhancing cybersecurity measures for low-cost, Wi-Fi-based Unmanned Aerial Vehicles (UAVs) against Distributed Denial of Service (DDoS) attacks. In the current work, we have explored three variants of DDoS attacks, namely Transmission Control Protocol (TCP), Internet Control Message Protocol (ICMP), and TCP + ICMP flooding attacks, and developed a detection mechanism that runs on the companion computer of the UAV system. As a part of the detection mechanism, we have evaluated various machine learning, and deep learning algorithms, such as XGBoost, Isolation Forest, Long Short-Term Memory (LSTM), Bidirectional-LSTM (Bi-LSTM), LSTM with attention, Bi-LSTM with attention, and Time Series Transformer (TST) in terms of various classification metrics. Our evaluation reveals that algorithms with attention mechanisms outperform their counterparts in general, and TST stands out as the most efficient model with a run time of 0.1 seconds. TST has demonstrated an F1 score of 0.999, 0.997, and 0.943 for TCP, ICMP, and TCP + ICMP flooding attacks respectively. In this work, we present the necessary steps required to build an on-board DDoS detection mechanism. Further, we also present the ablation study to identify the best TST hyperparameters for DDoS detection, and we have also underscored the advantage of adapting learnable positional embeddings in TST for DDoS detection with an improvement in F1 score from 0.94 to 0.99.