In the final weeks of campaigning, Argentine President-elect Javier Milei published a fabricated image depicting his Peronist rival Sergio Massa as an old-fashioned communist in military garb, his hand raised aloft in salute. The apparently AI-generated image drew some 3 million views when Milei posted it on a social media account, highlighting how the rival campaign teams used artificial intelligence technology to catch voters' attention in a bid to sway the race. "There were troubling signs of AI use" in the election, said Darrell West, a senior fellow at the Center for Technology Innovation at the Washington-based Brookings Institution.

After more than a century of concerted effort, physics still lacks basic principles of spontaneous self-organization. To appreciate why, we first state the problem, outline historical approaches, and survey the present state of the physics of self-organization. This frames the particular challenges arising from mathematical intractability and the resulting need for computational approaches, as well as those arising from a chronic failure to define structure. Then, an overview of two modern mathematical formulations of organization -- intrinsic computation and evolution operators -- lays out a way to overcome these challenges. Together, the vantage point they afford shows how to account for the emergence of structured states via a statistical mechanics of systems arbitrarily far from equilibrium. The result is a constructive path forward to principles of organization that builds on mathematical identification of structure.

Parameter-efficient fine-tuning (PEFT) techniques make it possible to efficiently adapt a language model to create "expert" models that specialize to new tasks or domains. Recent techniques in model merging and compositional generalization leverage these expert models by dynamically composing modules to improve zero/few-shot generalization. Despite the efficiency of PEFT methods, the size of expert models can make it onerous to retrieve expert models per query over high-latency networks like the Internet or serve multiple experts on a single GPU. To address these issues, we present ComPEFT, a novel method for compressing fine-tuning residuals (task vectors) of PEFT based models. ComPEFT employs sparsification and ternary quantization to reduce the size of the PEFT module without performing any additional retraining while preserving or enhancing model performance. In extensive evaluation across T5, T0, and LLaMA-based models with 200M - 65B parameters, ComPEFT achieves compression ratios of 8x - 50x. In particular, we show that ComPEFT improves with scale - stronger models exhibit higher compressibility and better performance. For example, we show that ComPEFT applied to LLaMA outperforms QLoRA by 4.16% on MMLU with a storage size reduction of up to 26x. In addition, we show that the compressed experts produced by ComPEFT maintain few-shot compositional generalization capabilities, facilitate efficient communication and computation, and exhibit enhanced performance when merged. Lastly, we provide an analysis of different method components, compare it with other PEFT methods, and test ComPEFT's efficacy for compressing the residual of full-finetuning. Our code is available at https://github.com/prateeky2806/compeft.

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high computational requirements and limited input sequence length. Despite these separate efforts, no investigation has been done into the intersection of these two fields. In this work, we provide an evaluation of model compression via knowledge distillation on efficient attention transformers. We provide cost-performance trade-offs for the compression of state-of-the-art efficient attention architectures and the gains made in performance in comparison to their full attention counterparts. Furthermore, we introduce a new long-context Named Entity Recognition dataset, GONERD, to train and test the performance of NER models on long sequences. We find that distilled efficient attention transformers can preserve a significant amount of original model performance, preserving up to 98.6% across short-context tasks (GLUE, SQUAD, CoNLL-2003), up to 94.6% across long-context Question-and-Answering tasks (HotpotQA, TriviaQA), and up to 98.8% on long-context Named Entity Recognition (GONERD), while decreasing inference times by up to 57.8%. We find that, for most models on most tasks, performing knowledge distillation is an effective method to yield high-performing efficient attention models with low costs.

Language models produce a distribution over the next token; can we use this to recover the prompt tokens? We consider the problem of language model inversion and show that next-token probabilities contain a surprising amount of information about the preceding text. Often we can recover the text in cases where it is hidden from the user, motivating a method for recovering unknown prompts given only the model's current distribution output. We consider a variety of model access scenarios, and show how even without predictions for every token in the vocabulary we can recover the probability vector through search. On Llama-2 7b, our inversion method reconstructs prompts with a BLEU of 59 and token-level F1 of 78 and recovers 27% of prompts exactly. Language models are autoregressive, outputting the probability of each next token in a sequence conditioned on the preceeding text. This distribution is used to generate future tokens in the sequence. Can this distribution also be used to reconstruct the prompt? In most contexts, this question is pointless, since we have already conditioned on this information. However, increasingly language models are being offered "as a service" where the user may have access to the outputs, but not all of the true prompt. In this context, it may be of interest to users to know the prompt and, perhaps, for the service provider to protect it. This goal has been the focus of "jailbreaking" approaches that attempt to use the forward text generation of the model to reveal the prompt. We formalize this problem of prompt reconstruction as language model inversion, recovering the input prompt conditioned on the language model's next-token probabilities. Interestingly, work in computer vision has shown that probability predictions of image classifiers retain a surprising amount of detail (Dosovitskiy & Brox, 2016), so it is plausible that this also holds for language models. We propose an architecture that predicts prompts by"unrolling" the distribution vector into a sequence that can be processed effectively by a pretrained encoder-decoder language model. This method shows for the first time that language model predictions are mostly invertible: in many cases, we are able to recover very similar inputs to the original, sometimes getting the input text back exactly.

We address the task of evidence retrieval for long document question answering, which involves locating relevant paragraphs within a document to answer a question. We aim to assess the applicability of large language models (LLMs) in the task of zero-shot long document evidence retrieval, owing to their unprecedented performance across various NLP tasks. However, currently the LLMs can consume limited context lengths as input, thus providing document chunks as inputs might overlook the global context while missing out on capturing the inter-segment dependencies. Moreover, directly feeding the large input sets can incur significant computational costs, particularly when processing the entire document (and potentially incurring monetary expenses with enterprise APIs like OpenAI's GPT variants). To address these challenges, we propose a suite of techniques that exploit the discourse structure commonly found in documents. By utilizing this structure, we create a condensed representation of the document, enabling a more comprehensive understanding and analysis of relationships between different parts. We retain $99.6\%$ of the best zero-shot approach's performance, while processing only $26\%$ of the total tokens used by the best approach in the information seeking evidence retrieval setup. We also show how our approach can be combined with \textit{self-ask} reasoning agent to achieve best zero-shot performance in complex multi-hop question answering, just $\approx 4\%$ short of zero-shot performance using gold evidence.

In safety-critical domains such as autonomous driving and medical diagnosis, the reliability of machine learning models is crucial. One significant challenge to reliability is concept drift, which can cause model deterioration over time. Traditionally, drift detectors rely on true labels, which are often scarce and costly. This study conducts a comprehensive empirical evaluation of using uncertainty values as substitutes for error rates in detecting drifts, aiming to alleviate the reliance on labeled post-deployment data. We examine five uncertainty estimation methods in conjunction with the ADWIN detector across seven real-world datasets. Our results reveal that while the SWAG method exhibits superior calibration, the overall accuracy in detecting drifts is not notably impacted by the choice of uncertainty estimation method, with even the most basic method demonstrating competitive performance. These findings offer valuable insights into the practical applicability of uncertainty-based drift detection in real-world, safety-critical applications.

State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual structural knowledge extraction. Two novel designs are incorporated. First, we propose to leverage the inherent structure of programming language to depict visual structural information. This approach enables explicit and consistent representation of visual structural information of multiple granularities, such as concepts, relations, and events, in a well-organized structured format. Second, we introduce curriculum-based learning for VLMs to progressively comprehend visual structures, from fundamental visual concepts to intricate event structures. Our intuition is that lower-level knowledge may contribute to complex visual structure understanding. Furthermore, we compile and release a collection of datasets tailored for visual structural knowledge extraction. We adopt a weakly-supervised approach to directly generate visual event structures from captions for ViStruct training, capitalizing on abundant image-caption pairs from the web. In experiments, we evaluate ViStruct on visual structure prediction tasks, demonstrating its effectiveness in improving the understanding of visual structures. The code is public at \url{https://github.com/Yangyi-Chen/vi-struct}.

Completely Automated Public Turing test to tell Computers and Humans Apart, short for CAPTCHA, is an essential and relatively easy way to defend against malicious attacks implemented by bots. The security and usability trade-off limits the use of massive geometric transformations to interfere deep model recognition and deep models even outperformed humans in complex CAPTCHAs. The discovery of adversarial examples provides an ideal solution to the security and usability trade-off by integrating adversarial examples and CAPTCHAs to generate adversarial CAPTCHAs that can fool the deep models. In this paper, we extend the definition of adversarial CAPTCHAs and propose a classification method for adversarial CAPTCHAs. Then we systematically review some commonly used methods to generate adversarial examples and methods that are successfully used to generate adversarial CAPTCHAs. Also, we analyze some defense methods that can be used to defend adversarial CAPTCHAs, indicating potential threats to adversarial CAPTCHAs. Finally, we discuss some possible future research directions for adversarial CAPTCHAs at the end of this paper.

Breast cancer is a serious disease that inflicts millions of people each year, and the number of cases is increasing. Early detection is the best way to reduce the impact of the disease. Researchers have developed many techniques to detect breast cancer, including the use of histopathology images in CAD systems. This research proposes a technique that combine already fully trained model using adaptive average ensemble, this is different from the literature which uses average ensemble before training and the average ensemble is trained simultaneously. Our approach is different because it used adaptive average ensemble after training which has increased the performance of evaluation metrics. It averages the outputs of every trained model, and every model will have weight according to its accuracy. The accuracy in the adaptive weighted ensemble model has achieved 98% where the accuracy has increased by 1 percent which is better than the best participating model in the ensemble which was 97%. Also, it decreased the numbers of false positive and false negative and enhanced the performance metrics.