Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models. First, we taxonomize the vast space of potential scenarios (i.e. use cases) and metrics (i.e. desiderata) that are of interest for LMs. Then we select a broad subset based on coverage and feasibility, noting what's missing or underrepresented (e.g. question answering for neglected English dialects, metrics for trustworthiness). Second, we adopt a multi-metric approach: We measure 7 metrics (accuracy, calibration, robustness, fairness, bias, toxicity, and efficiency) for each of 16 core scenarios when possible (87.5% of the time). This ensures metrics beyond accuracy don't fall to the wayside, and that trade-offs are clearly exposed. We also perform 7 targeted evaluations, based on 26 targeted scenarios, to analyze specific aspects (e.g. reasoning, disinformation). Third, we conduct a large-scale evaluation of 30 prominent language models (spanning open, limited-access, and closed models) on all 42 scenarios, 21 of which were not previously used in mainstream LM evaluation. Prior to HELM, models on average were evaluated on just 17.9% of the core HELM scenarios, with some prominent models not sharing a single scenario in common. We improve this to 96.0%: now all 30 models have been densely benchmarked on the same core scenarios and metrics under standardized conditions. Our evaluation surfaces 25 top-level findings. For full transparency, we release all raw model prompts and completions publicly for further analysis, as well as a general modular toolkit. We intend for HELM to be a living benchmark for the community, continuously updated with new scenarios, metrics, and models.

Quantum state tomography (QST) is the process of reconstructing the complete state of a quantum system (mathematically described as a density matrix) through a series of different measurements. These measurements are performed on a number of identical copies of the quantum system, with outcomes gathered as frequencies. QST aims to recover the density matrix and the corresponding properties of the quantum state from the measured frequencies. Although an informationally complete set of measurements can specify quantum state accurately in an ideal scenario with a large number of identical copies, both measurements and identical copies are restricted and imperfect in practical scenarios, making QST highly ill-posed. The conventional QST methods usually assume adequate or accurate measured frequencies or rely on manually designed regularizers to handle the ill-posed reconstruction problem, suffering from limited applications in realistic scenarios. Recent advances in deep neural networks (DNNs) led to the emergence of deep learning (DL) in QST. However, existing DL-based QST approaches often employ generic DNN models that are not optimized for imperfect conditions of QST. In this paper, we propose a transformer-based autoencoder architecture tailored for QST with imperfect measurement data. Our method leverages a transformer-based encoder to extract an informative latent representation (ILR) from imperfect measurement data and employs a decoder to predict the quantum states based on the ILR. We anticipate that the high-dimensional ILR will capture more comprehensive information about quantum states. To achieve this, we conduct pre-training of the encoder using a pretext task that involves reconstructing high-quality frequencies from measured frequencies. Extensive simulations and experiments demonstrate the remarkable ability of the ILR in dealing with imperfect measurement data in QST.

Authorship identification ascertains the authorship of texts whose origins remain undisclosed. That authorship identification techniques work as reliably as they do has been attributed to the fact that authorial style is properly captured and represented. Although modern authorship identification methods have evolved significantly over the years and have proven effective in distinguishing authorial styles, the generalization of stylistic features across domains has not been systematically reviewed. The presented work addresses the challenge of enhancing the generalization of stylistic representations in authorship identification, particularly when there are discrepancies between training and testing samples. A comprehensive review of empirical studies was conducted, focusing on various stylistic features and their effectiveness in representing an author's style. The influencing factors such as topic, genre, and register on writing style were also explored, along with strategies to mitigate their impact. While some stylistic features, like character n-grams and function words, have proven to be robust and discriminative, others, such as content words, can introduce biases and hinder cross-domain generalization. Representations learned using deep learning models, especially those incorporating character n-grams and syntactic information, show promise in enhancing representation generalization. The findings underscore the importance of selecting appropriate stylistic features for authorship identification, especially in cross-domain scenarios. The recognition of the strengths and weaknesses of various linguistic features paves the way for more accurate authorship identification in diverse contexts.

Recent works on SLAM extend their pose graphs with higher-level semantic concepts exploiting relationships between them, to provide, not only a richer representation of the situation/environment but also to improve the accuracy of its estimation. Concretely, our previous work, Situational Graphs (S-Graphs), a pioneer in jointly leveraging semantic relationships in the factor optimization process, relies on semantic entities such as wall surfaces and rooms, whose relationship is mathematically defined. Nevertheless, excerpting these high-level concepts relying exclusively on the lower-level factor-graph remains a challenge and it is currently done with ad-hoc algorithms, which limits its capability to include new semantic-relational concepts. To overcome this limitation, in this work, we propose a Graph Neural Network (GNN) for learning high-level semantic-relational concepts that can be inferred from the low-level factor graph. We have demonstrated that we can infer room entities and their relationship to the mapped wall surfaces, more accurately and more computationally efficient than the baseline algorithm. Additionally, to demonstrate the versatility of our method, we provide a new semantic concept, i.e. wall, and its relationship with its wall surfaces. Our proposed method has been integrated into S-Graphs+, and it has been validated in both simulated and real datasets. A docker container with our software will be made available to the scientific community.

Robots for physical Human-Robot Collaboration (pHRC) systems need to change their behavior and how they operate in consideration of several factors, such as the performance and intention of a human co-worker and the capabilities of different human-co-workers in collision avoidance and singularity of the robot operation. As the system's admittance becomes variable throughout the workspace, a potential solution is to tune the interaction forces and control the parameters based on the operator's requirements. To overcome this issue, we have demonstrated a novel closed-loop-neuroadaptive framework for pHRC. We have applied cognitive conflict information in a closed-loop manner, with the help of reinforcement learning, to adapt to robot strategy and compare this with open-loop settings. The experiment results show that the closed-loop-based neuroadaptive framework successfully reduces the level of cognitive conflict during pHRC, consequently increasing the smoothness and intuitiveness of human-robot collaboration. These results suggest the feasibility of a neuroadaptive approach for future pHRC control systems through electroencephalogram (EEG) signals.

Learning from demonstration is one of the most promising methods to counteract the challenging long-term trends in repetitive industrial assembly. It offers not only a programming technique that is accessible to workers on the shop floor, reducing the need for robot experts and the associated costs but also a possible solution to the observable shift from mass-production to mass-customisation through flexible and generalising systems. Since the emergence of the learning from demonstration idea in the 1980s, its methodologies, capabilities, and achievements have constantly evolved. However, despite reports of continued progress in academic publications, the concept has not yet robustly emerged across the assembly industry. In light of its great potential, this paper presents the findings from a systematic literature review following the updated Preferred Reporting Items for Systematic Reviews (PRISMA) guidelines. It aims to provide an overview of the state-of-the-art learning from demonstration solutions developed for assembly-related tasks and offer a critical discussion of remaining obstacles in order to drive its progression towards meaningful deployments. The analysis includes a total of 61 papers over the period of 2013-2023 sourced from Scopus and Web of Science databases. Findings indicate that learning from demonstration has attained a significant level of maturity within the research environment, as evidenced by thorough experimental achievements, proving its great promise for industrial assembly applications. However, critical obstacles exist in the area of proven practicability, task complexity and diversity, generalisation, performance evaluation and integration concepts that require attention to promote its widespread adoption and create a seamless transition into industrial practices.

Paradoxical decision-making behaviours such as preference reversal often arise from imprecise or noisy human preferences. By harnessing the physical principle of magnetisation reversal in ferromagnetic nanostructures driven by electric current, we developed a model that closely reflects human decision-making dynamics. Tested against a spectrum of psychological data, our model adeptly captures the complexities inherent in individual choices. This blend of physics and psychology paves the way for fresh perspectives on understanding human decision-making processes.

We study the effect of tokenization on gender bias in machine translation, an aspect that has been largely overlooked in previous works. Specifically, we focus on the interactions between the frequency of gendered profession names in training data, their representation in the subword tokenizer's vocabulary, and gender bias. We observe that female and non-stereotypical gender inflections of profession names (e.g., Spanish "doctora" for "female doctor") tend to be split into multiple subword tokens. Our results indicate that the imbalance of gender forms in the model's training corpus is a major factor contributing to gender bias and has a greater impact than subword splitting. We show that analyzing subword splits provides good estimates of gender-form imbalance in the training data and can be used even when the corpus is not publicly available. We also demonstrate that fine-tuning just the token embedding layer can decrease the gap in gender prediction accuracy between female and male forms without impairing the translation quality.

The rise in popularity of Large Language Models (LLMs) has prompted discussions in academic circles, with students exploring LLM-based tools for coursework inquiries and instructors exploring them for teaching and research. Even though a lot of work is underway to create LLM-based tools tailored for students and instructors, there is a lack of comprehensive user studies that capture the perspectives of students and instructors regarding LLMs. This paper addresses this gap by conducting surveys and interviews within undergraduate engineering universities in India. Using 1306 survey responses among students, 112 student interviews, and 27 instructor interviews around the academic usage of ChatGPT (a popular LLM), this paper offers insights into the current usage patterns, perceived benefits, threats, and challenges, as well as recommendations for enhancing the adoption of LLMs among students and instructors. These insights are further utilized to discuss the practical implications of LLMs in undergraduate engineering education and beyond.

Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific training data in the form of (passage, target structure) pairs to obtain reasonable performance. However, obtaining such data through human annotation is costly, leading to a pressing need for low-resource information extraction approaches that require minimal human labeling for real-world applications. Fine-tuning supervised models with synthesized training data would be a generalizable method, but the existing data generation methods either still rely on large-scale ground-truth data or cannot be applied to complicated IE tasks due to their poor performance. To address these challenges, we propose STAR, a data generation method that leverages Large Language Models (LLMs) to synthesize data instances given limited seed demonstrations, thereby boosting low-resource information extraction performance. Our approach involves generating target structures (Y) followed by generating passages (X), all accomplished with the aid of LLMs. We design fine-grained step-by-step instructions to obtain the initial data instances. We further reduce errors and improve data quality through self-reflection error identification and self-refinement with iterative revision. Our experiments show that the data generated by STAR significantly improves the performance of low-resource event extraction and relation extraction tasks, even surpassing the effectiveness of human-curated data. Human assessment of the data quality shows STAR-generated data exhibits higher passage quality and better align with the task definitions compared with the human-curated data.