Recommender Systems (RS) play an integral role in enhancing user experiences by providing personalized item suggestions. This survey reviews the progress in RS inclusively from 2017 to 2024, effectively connecting theoretical advances with practical applications. We explore the development from traditional RS techniques like content-based and collaborative filtering to advanced methods involving deep learning, graph-based models, reinforcement learning, and large language models. We also discuss specialized systems such as context-aware, review-based, and fairness-aware RS. The primary goal of this survey is to bridge theory with practice. It addresses challenges across various sectors, including e-commerce, healthcare, and finance, emphasizing the need for scalable, real-time, and trustworthy solutions. Through this survey, we promote stronger partnerships between academic research and industry practices. The insights offered by this survey aim to guide industry professionals in optimizing RS deployment and to inspire future research directions, especially in addressing emerging technological and societal trends

One way to increase confidence in the outputs of Large Language Models (LLMs) is to support them with reasoning that is clear and easy to check -- a property we call legibility. We study legibility in the context of solving grade-school math problems and show that optimizing chain-of-thought solutions only for answer correctness can make them less legible. To mitigate the loss in legibility, we propose a training algorithm inspired by Prover-Verifier Game from Anil et al. (2021). Our algorithm iteratively trains small verifiers to predict solution correctness, "helpful" provers to produce correct solutions that the verifier accepts, and "sneaky" provers to produce incorrect solutions that fool the verifier. We find that the helpful prover's accuracy and the verifier's robustness to adversarial attacks increase over the course of training. Furthermore, we show that legibility training transfers to time-constrained humans tasked with verifying solution correctness. Over course of LLM training human accuracy increases when checking the helpful prover's solutions, and decreases when checking the sneaky prover's solutions. Hence, training for checkability by small verifiers is a plausible technique for increasing output legibility. Our results suggest legibility training against small verifiers as a practical avenue for increasing legibility of large LLMs to humans, and thus could help with alignment of superhuman models.

Distributed execution of deep learning training involves a dynamic interplay between hardware accelerator architecture and device placement strategy. This is the first work to explore the co-optimization of determining the optimal architecture and device placement strategy through novel algorithms, improving the balance of computational resources, memory usage, and data distribution. Our architecture search leverages tensor and vector units, determining their quantity and dimensionality, and on-chip and off-chip memory configurations. It also determines the microbatch size and decides whether to recompute or stash activations, balancing the memory footprint of training and storage size. For each explored architecture configuration, we use an Integer Linear Program (ILP) to find the optimal schedule for executing operators on the accelerator. The ILP results then integrate with a dynamic programming solution to identify the most effective device placement strategy, combining data, pipeline, and tensor model parallelism across multiple accelerators. Our approach achieves higher throughput on large language models compared to the state-of-the-art TPUv4 and the Spotlight accelerator search framework. The entire source code of PHAZE is available at https://github.com/msr-fiddle/phaze.

Natural Language Processing has moved rather quickly from modelling specific tasks to taking more general pre-trained models and fine-tuning them for specific tasks, to a point where we now have what appear to be inherently generalist models. This paper argues that the resultant loss of clarity on what these models model leads to metaphors like "artificial general intelligences" that are not helpful for evaluating their strengths and weaknesses. The proposal is to see their generality, and their potential value, in their ability to approximate specialist function, based on a natural language specification. This framing brings to the fore questions of the quality of the approximation, but beyond that, also questions of discoverability, stability, and protectability of these functions. As the paper will show, this framing hence brings together in one conceptual framework various aspects of evaluation, both from a practical and a theoretical perspective, as well as questions often relegated to a secondary status (such as "prompt injection" and "jailbreaking").

Recent advancements in Language Models (LMs) have catalyzed the creation of multiple benchmarks, designed to assess these models' general capabilities. A crucial task, however, is assessing the validity of the benchmarks themselves. This is most commonly done via Benchmark Agreement Testing (BAT), where new benchmarks are validated against established ones using some agreement metric (e.g., rank correlation). Despite the crucial role of BAT for benchmark builders and consumers, there are no standardized procedures for such agreement testing. This deficiency can lead to invalid conclusions, fostering mistrust in benchmarks and upending the ability to properly choose the appropriate benchmark to use. By analyzing over 40 prominent benchmarks, we demonstrate how some overlooked methodological choices can significantly influence BAT results, potentially undermining the validity of conclusions. To address these inconsistencies, we propose a set of best practices for BAT and demonstrate how utilizing these methodologies greatly improves BAT robustness and validity. To foster adoption and facilitate future research,, we introduce BenchBench, a python package for BAT, and release the BenchBench-leaderboard, a meta-benchmark designed to evaluate benchmarks using their peers. Our findings underscore the necessity for standardized BAT, ensuring the robustness and validity of benchmark evaluations in the evolving landscape of language model research. BenchBench Package: https://github.com/IBM/BenchBench Leaderboard: https://huggingface.co/spaces/per/BenchBench

Understanding human behavior is a fundamental goal of social sciences, yet its analysis presents significant challenges. Conventional methodologies employed for the study of behavior, characterized by labor-intensive data collection processes and intricate analyses, frequently hinder comprehensive exploration due to their time and resource demands. In response to these challenges, computational models have proven to be promising tools that help researchers analyze large amounts of data by automatically identifying important behavioral indicators, such as social signals. However, the widespread adoption of such state-of-the-art computational models is impeded by their inherent complexity and the substantial computational resources necessary to run them, thereby constraining accessibility for researchers without technical expertise and adequate equipment. To address these barriers, we introduce DISCOVER -- a modular and flexible, yet user-friendly software framework specifically developed to streamline computational-driven data exploration for human behavior analysis. Our primary objective is to democratize access to advanced computational methodologies, thereby enabling researchers across disciplines to engage in detailed behavioral analysis without the need for extensive technical proficiency. In this paper, we demonstrate the capabilities of DISCOVER using four exemplary data exploration workflows that build on each other: Interactive Semantic Content Exploration, Visual Inspection, Aided Annotation, and Multimodal Scene Search. By illustrating these workflows, we aim to emphasize the versatility and accessibility of DISCOVER as a comprehensive framework and propose a set of blueprints that can serve as a general starting point for exploratory data analysis.

Research in the field of language models is rapidly evolving, with many open models being released to the public. Openly available pretraining corpora usually focus on only a handful of languages, with many others either missing completely or extremely underrepresented. In this report, we introduce FuLG, a hundred-fifty-billion-token Romanian corpus extracted from CommonCrawl. We present our methodology for filtering FuLG and compare it via ablation studies against existing Romanian corpora.

Identifying the reason for which an author cites another work is essential to understand the nature of scientific contributions and to assess their impact. Citations are one of the pillars of scholarly communication and most metrics employed to analyze these conceptual links are based on quantitative observations. Behind the act of referencing another scholarly work there is a whole world of meanings that needs to be proficiently and effectively revealed. This study emphasizes the importance of trustfully classifying citation intents to provide more comprehensive and insightful analyses in research assessment. We address this task by presenting a study utilizing advanced Ensemble Strategies for Citation Intent Classification (CIC) incorporating Language Models (LMs) and employing Explainable AI (XAI) techniques to enhance the interpretability and trustworthiness of models' predictions. Our approach involves two ensemble classifiers that utilize fine-tuned SciBERT and XLNet LMs as baselines. We further demonstrate the critical role of section titles as a feature in improving models' performances. The study also introduces a web application developed with Flask and currently available at http://137.204.64.4:81/cic/classifier, aimed at classifying citation intents. One of our models sets as a new state-of-the-art (SOTA) with an 89.46% Macro-F1 score on the SciCite benchmark. The integration of XAI techniques provides insights into the decision-making processes, highlighting the contributions of individual words for level-0 classifications, and of individual models for the metaclassification. The findings suggest that the inclusion of section titles significantly enhances classification performances in the CIC task. Our contributions provide useful insights for developing more robust datasets and methodologies, thus fostering a deeper understanding of scholarly communication.

Imposing constraints on machine translation systems presents a challenging issue because these systems are not trained to make use of constraints in generating adequate, fluent translations. In this paper, we leverage the capabilities of large language models (LLMs) for constrained translation, given that LLMs can easily adapt to this task by taking translation instructions and constraints as prompts. However, LLMs cannot always guarantee the adequacy of translation, and, in some cases, ignore the given constraints. This is in part because LLMs might be overly confident in their predictions, overriding the influence of the constraints. To overcome this overiding behaviour, we propose to add a revision process that encourages LLMs to correct the outputs by prompting them about the constraints that have not yet been met. We evaluate our approach on four constrained translation tasks, encompassing both lexical and structural constraints in multiple constraint domains. Experiments show 15\% improvement in constraint-based translation accuracy over standard LLMs and the approach also significantly outperforms neural machine translation (NMT) state-of-the-art methods.

One core capability of large language models (LLMs) is to follow natural language instructions. However, the issue of automatically constructing high-quality training data to enhance the complex instruction-following abilities of LLMs without manual annotation remains unresolved. IF transforms the validation of instruction-following data quality into code verification, requiring LLMs to generate instructions, the corresponding code to check the correctness of the instruction responses, and unit test samples to verify the code's correctness. Then, execution feedbackbased rejection sampling can generate data for Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) training. IF achieves significant improvements across three training algorithms, SFT, Offline DPO, and Online DPO, when applied to the top open-source LLMs, Qwen2 and LLaMA3, in self-alignment and strong-to-weak distillation settings. Our code is publicly available at https://github.com/QwenLM/AutoIF. Keep your response under 20 characters in length. Are you familiar with OET or Occupational English Test? What is the weather like today? Response 2:The weather is sunny and it Response Response 2:Yes, I'm familiar with OET. The instruction-following ability of large language models (LLMs) refers to their capacity to understand, interpret, and execute commands given to them in natural language (Lou et al., 2023; OpenAI et al., 2024). This ability is fundamental to contemporary LLMs as it enables them to leverage their underlying knowledge, interact intuitively with users (Ouyang et al., 2022), adapt to various requirements (Zhang et al., 2023), and perform complex tasks (Sun et al., 2024).