The increasing reliance on online recruitment platforms coupled with the adoption of AI technologies has highlighted the critical need for efficient resume classification methods. However, challenges such as small datasets, lack of standardized resume templates, and privacy concerns hinder the accuracy and effectiveness of existing classification models. In this work, we address these challenges by presenting a comprehensive approach to resume classification. We curated a large-scale dataset of 13,389 resumes from diverse sources and employed Large Language Models (LLMs) such as BERT and Gemma1.1 2B for classification. Our results demonstrate significant improvements over traditional machine learning approaches, with our best model achieving a top-1 accuracy of 92\% and a top-5 accuracy of 97.5\%. These findings underscore the importance of dataset quality and advanced model architectures in enhancing the accuracy and robustness of resume classification systems, thus advancing the field of online recruitment practices.

Recent studies show evidence for emergent cognitive abilities in Large Pre-trained Language Models (PLMs). The increasing cognitive alignment of these models has made them candidates for cognitive science theories. Prior research into the emergent cognitive abilities of PLMs has largely been path-independent to model training, i.e., has focused on the final model weights and not the intermediate steps. However, building plausible models of human cognition using PLMs would benefit from considering the developmental alignment of their performance during training to the trajectories of children's thinking. Guided by psychometric tests of human intelligence, we choose four sets of tasks to investigate the alignment of ten popular families of PLMs and evaluate their available intermediate and final training steps. These tasks are Numerical ability, Linguistic abilities, Conceptual understanding, and Fluid reasoning. We find a striking regularity: regardless of model size, the developmental trajectories of PLMs consistently exhibit a window of maximal alignment to human cognitive development. Before that window, training appears to endow "blank slate" models with the requisite structure to be poised to rapidly learn from experience. After that window, training appears to serve the engineering goal of reducing loss but not the scientific goal of increasing alignment with human cognition.

With the rapid development of Large Language Models (LLMs), it is crucial to have benchmarks which can evaluate the ability of LLMs on different domains. One common use of LLMs is performing tasks on scientific topics, such as writing algorithms, querying databases or giving mathematical proofs. Inspired by the way university students are evaluated on such tasks, in this paper, we propose SciEx - a benchmark consisting of university computer science exam questions, to evaluate LLMs ability on solving scientific tasks. SciEx is (1) multilingual, containing both English and German exams, and (2) multi-modal, containing questions that involve images, and (3) contains various types of freeform questions with different difficulty levels, due to the nature of university exams. We evaluate the performance of various state-of-the-art LLMs on our new benchmark. Since SciEx questions are freeform, it is not straightforward to evaluate LLM performance. Therefore, we provide human expert grading of the LLM outputs on SciEx. We show that the free-form exams in SciEx remain challenging for the current LLMs, where the best LLM only achieves 59.4\% exam grade on average. We also provide detailed comparisons between LLM performance and student performance on SciEx. To enable future evaluation of new LLMs, we propose using LLM-as-a-judge to grade the LLM answers on SciEx. Our experiments show that, although they do not perform perfectly on solving the exams, LLMs are decent as graders, achieving 0.948 Pearson correlation with expert grading.

Swift and accurate detection of specified objects is crucial for many industrial applications, such as safety monitoring on construction sites. However, traditional approaches rely heavily on arduous manual annotation and data collection, which struggle to adapt to ever-changing environments and novel target objects. To address these limitations, this paper presents DART, an automated end-to-end pipeline designed to streamline the entire workflow of an object detection application from data collection to model deployment. DART eliminates the need for human labeling and extensive data collection while excelling in diverse scenarios. It employs a subject-driven image generation module (DreamBooth with SDXL) for data diversification, followed by an annotation stage where open-vocabulary object detection (Grounding DINO) generates bounding box annotations for both generated and original images. These pseudo-labels are then reviewed by a large multimodal model (GPT-4o) to guarantee credibility before serving as ground truth to train real-time object detectors (YOLO). We apply DART to a self-collected dataset of construction machines named Liebherr Product, which contains over 15K high-quality images across 23 categories. The current implementation of DART significantly increases average precision (AP) from 0.064 to 0.832. Furthermore, we adopt a modular design for DART to ensure easy exchangeability and extensibility. This allows for a smooth transition to more advanced algorithms in the future, seamless integration of new object categories without manual labeling, and adaptability to customized environments without extra data collection. The code and dataset are released at https://github.com/chen-xin-94/DART.

With increasingly sophisticated large language models (LLMs), the potential for abuse rises drastically. As a submission to the Swiss AI Safety Prize, we present a novel type of metamorphic malware leveraging LLMs for two key processes. First, LLMs are used for automatic code rewriting to evade signature-based detection by antimalware programs. The malware then spreads its copies via email by utilizing an LLM to socially engineer email replies to encourage recipients to execute the attached malware. Our submission includes a functional minimal prototype, highlighting the risks that LLMs pose for cybersecurity and underscoring the need for further research into intelligent malware.

Science journalism reports current scientific discoveries to non-specialists, aiming to enable public comprehension of the state of the art. However, this task can be challenging as the audience often lacks specific knowledge about the presented research. To address this challenge, we propose a framework that integrates three LLMs mimicking the real-world writing-reading-feedback-revision workflow, with one LLM acting as the journalist, a smaller LLM as the general public reader, and the third LLM as an editor. The journalist's writing is iteratively refined by feedback from the reader and suggestions from the editor. Our experiments demonstrate that by leveraging the collaboration of two 7B and one 1.8B open-source LLMs, we can generate articles that are more accessible than those generated by existing methods, including advanced models such as GPT-4.

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with "circuit breakers." Existing techniques aimed at improving alignment, such as refusal training, are often bypassed. Techniques such as adversarial training try to plug these holes by countering specific attacks. As an alternative to refusal training and adversarial training, circuit-breaking directly controls the representations that are responsible for harmful outputs in the first place. Our technique can be applied to both text-only and multimodal language models to prevent the generation of harmful outputs without sacrificing utility -- even in the presence of powerful unseen attacks. Notably, while adversarial robustness in standalone image recognition remains an open challenge, circuit breakers allow the larger multimodal system to reliably withstand image "hijacks" that aim to produce harmful content. Finally, we extend our approach to AI agents, demonstrating considerable reductions in the rate of harmful actions when they are under attack. Our approach represents a significant step forward in the development of reliable safeguards to harmful behavior and adversarial attacks.

Having a clean dataset has been the foundational assumption of most natural language processing (NLP) systems. However, properly written text is rarely found in real-world scenarios and hence, oftentimes invalidates the aforementioned foundational assumption. Recently, Large language models (LLMs) have shown impressive performance, but can they handle the inevitable noise in real-world data? This work tackles this critical question by investigating LLMs' resilience against morphological variations in text. To that end, we artificially introduce varying levels of noise into a diverse set of datasets and systematically evaluate LLMs' robustness against the corrupt variations of the original text. Our findings show that contrary to popular beliefs, generative LLMs are quiet robust to noisy perturbations in text. This is a departure from pre-trained models like BERT or RoBERTa whose performance has been shown to be sensitive to deteriorating noisy text. Additionally, we test LLMs' resilience on multiple real-world benchmarks that closely mimic commonly found errors in the wild. With minimal prompting, LLMs achieve a new state-of-the-art on the benchmark tasks of Grammar Error Correction (GEC) and Lexical Semantic Change (LSC). To empower future research, we also release a dataset annotated by humans stating their preference for LLM vs. human-corrected outputs along with the code to reproduce our results.

Trustworthiness and interpretability are inextricably linked concepts for LLMs. The more interpretable an LLM is, the more trustworthy it becomes. However, current techniques for interpreting LLMs when applied to code-related tasks largely focus on accuracy measurements, measures of how models react to change, or individual task performance instead of the fine-grained explanations needed at prediction time for greater interpretability, and hence trust. To improve upon this status quo, this paper introduces ASTrust, an interpretability method for LLMs of code that generates explanations grounded in the relationship between model confidence and syntactic structures of programming languages. ASTrust explains generated code in the context of syntax categories based on Abstract Syntax Trees and aids practitioners in understanding model predictions at both local (individual code snippets) and global (larger datasets of code) levels. By distributing and assigning model confidence scores to well-known syntactic structures that exist within ASTs, our approach moves beyond prior techniques that perform token-level confidence mapping by offering a view of model confidence that directly aligns with programming language concepts with which developers are familiar. To put ASTrust into practice, we developed an automated visualization that illustrates the aggregated model confidence scores superimposed on sequence, heat-map, and graph-based visuals of syntactic structures from ASTs. We examine both the practical benefit that ASTrust can provide through a data science study on 12 popular LLMs on a curated set of GitHub repos and the usefulness of ASTrust through a human study.

Large language models (LLMs) have shown remarkable capabilities, but still struggle with processing extensive contexts, limiting their ability to maintain coherence and accuracy over long sequences. In this work, we introduce EM-LLM, a novel approach that integrates key aspects of human episodic memory and event cognition into LLMs, enabling them to effectively handle practically infinite context lengths while maintaining computational efficiency. When needed, these events are retrieved through a two-stage memory process, combining similarity-based and temporally contiguous retrieval for efficient and human-like access to relevant information. Experiments on the LongBench dataset demonstrate EM-LLM's superior performance, outperforming the state-of-the-art InfLLM model with an overall relative improvement of 4.3% across various tasks, including a 33% improvement on the PassageRetrieval task. Furthermore, our analysis reveals strong correlations between EM-LLM's event segmentation and human-perceived events, suggesting a bridge between this artificial system and its biological counterpart. This work not only advances LLM capabilities in processing extended contexts but also provides a computational framework for exploring human memory mechanisms, opening new avenues for interdisciplinary research in AI and cognitive science. For contemporary pre-trained large language models (LLMs), the context window serves as the primary mechanism to incorporate domain-specific, private, or common up-to-date information. These limitations stem from inherent challenges in Transformer-based architectures. Recent studies have shown that Transformers struggle with extrapolating to contexts longer than their training window size (Kazemnejad et al., 2024). On top of this, employing softmax attention over extended token sequences requires substantial computational resources for each token generation, and the resulting attention embeddings risk becoming excessively noisy and losing their distinctiveness (Tworkowski et al., 2023). To mitigate those challenges, recent works have focused on retrieval-based methods, either in the form of in-context augmentation (e.g., RAG-based techniques (Lewis et al., 2020; Gao et al., 2024)) or via retrieval of previously-inferred key-value pairs (KV) within individual attention heads (Wu et al., 2022; Tworkowski et al., 2023; Bertsch et al., 2023).