Automatic melody-to-lyric generation aims to produce lyrics that align with a given melody. Although previous work can generate lyrics based on high-level control signals, such as keywords or genre, they often struggle with three challenges: (1) lack of controllability, as prior works are only able to produce lyrics from scratch, with little or no control over the content; (2) inability to generate fully structured songs with the desired format; and (3) failure to align prominent words in the lyrics with prominent notes in the melody, resulting in poor lyrics-melody alignment. In this work, we introduce REFFLY (REvision Framework For Lyrics), the first revision framework designed to edit arbitrary forms of plain text draft into high-quality, full-fledged song lyrics. Our approach ensures that the generated lyrics retain the original meaning of the draft, align with the melody, and adhere to the desired song structures. We demonstrate that REFFLY performs well in diverse task settings, such as lyrics revision and song translation. Experimental results show that our model outperforms strong baselines, such as Lyra (Tian et al. 2023) and GPT-4, by 25% in both musicality and text quality.

Teaching new information to pre-trained large language models (PLM) is a crucial but challenging task. Model adaptation techniques, such as fine-tuning and parameter-efficient training have been shown to store new facts at a slow rate; continual learning is an option but is costly and prone to catastrophic forgetting. This work studies and quantifies how PLM may learn and remember new world knowledge facts that do not occur in their pre-training corpus, which only contains world knowledge up to a certain date. To that purpose, we first propose Novel-WD, a new dataset consisting of sentences containing novel facts extracted from recent Wikidata updates, along with two evaluation tasks in the form of causal language modeling and multiple choice questions (MCQ). We make this dataset freely available to the community, and release a procedure to later build new versions of similar datasets with up-to-date information. We also explore the use of prefix-tuning for novel information learning, and analyze how much information can be stored within a given prefix. We show that a single fact can reliably be encoded within a single prefix, and that the prefix capacity increases with its length and with the base model size.

This article provides a critical overview of the recently approved Artificial Intelligence Act. It starts by presenting the main structure, objectives, and approach of Regulation (EU) 2024/1689. A definition of key concepts follows, and then the material and territorial scope, as well as the timing of application, are analyzed. Although the Regulation does not explicitly set out principles, the main ideas of fairness, accountability, transparency, and equity in AI underly a set of rules of the regulation. This is discussed before looking at the ill-defined set of forbidden AI practices (manipulation and e exploitation of vulnerabilities, social scoring, biometric identification and classification, and predictive policing). It is highlighted that those rules deal with behaviors rather than AI systems. The qualification and regulation of high-risk AI systems are tackled, alongside the obligation of transparency for certain systems, the regulation of general-purpose models, and the rules on certification, supervision, and sanctions. The text concludes that even if the overall framework can be deemed adequate and balanced, the approach is so complex that it risks defeating its own purpose of promoting responsible innovation within the European Union and beyond its borders.

Recently, there has been an increasing interest in the construction of general-domain and domain-specific causal knowledge graphs. Such knowledge graphs enable reasoning for causal analysis and event prediction, and so have a range of applications across different domains. While great progress has been made toward automated construction of causal knowledge graphs, the evaluation of such solutions has either focused on low-level tasks (e.g., cause-effect phrase extraction) or on ad hoc evaluation data and small manual evaluations. In this Resource Track paper, we present a corpus, task, and evaluation framework for causal knowledge graph construction. Our corpus consists of Wikipedia articles for a collection of event-related concepts in Wikidata. The task is to extract causal relations between event concepts from the corpus. The evaluation is performed in part using existing causal relations in Wikidata to measure recall, and in part using Large Language Models to avoid the need for manual or crowd-sourced evaluation. We evaluate a pipeline for causal knowledge graph construction that relies on neural models for question answering and concept linking, and show how the corpus and the evaluation framework allow us to effectively find the right model for each task. The corpus and the evaluation framework are publicly available.

Public transportation systems are experiencing an increase in commuter traffic. This increase underscores the need for resilience strategies to manage unexpected service disruptions, ensuring rapid and effective responses that minimize adverse effects on stakeholders and enhance the system's ability to maintain essential functions and recover quickly. This study aims to explore the management of public transport disruptions through resilience as a service (RaaS) strategies, developing an optimization model to effectively allocate resources and minimize the cost for operators and passengers. The proposed model includes multiple transportation options, such as buses, taxis, and automated vans, and evaluates them as bridging alternatives to rail-disrupted services based on factors such as their availability, capacity, speed, and proximity to the disrupted station. This ensures that the most suitable vehicles are deployed to maintain service continuity. Applied to a case study in the Ile de France region, Paris and suburbs, complemented by a microscopic simulation, the model is compared to existing solutions such as bus bridging and reserve fleets. The results highlight the model's performance in minimizing costs and enhancing stakeholder satisfaction, optimizing transport management during disruptions.

The increasing demand for high-quality datasets in machine learning has raised concerns about the ethical and responsible creation of these datasets. Dataset creators play a crucial role in developing responsible practices, yet their perspectives and expertise have not yet been highlighted in the current literature. In this paper, we bridge this gap by presenting insights from a qualitative study that included interviewing 18 leading dataset creators about the current state of the field. We shed light on the challenges and considerations faced by dataset creators, and our findings underscore the potential for deeper collaboration, knowledge sharing, and collective development. Through a close analysis of their perspectives, we share seven central recommendations for improving responsible dataset creation, including issues such as data quality, documentation, privacy and consent, and how to mitigate potential harms from unintended use cases. By fostering critical reflection and sharing the experiences of dataset creators, we aim to promote responsible dataset creation practices and develop a nuanced understanding of this crucial but often undervalued aspect of machine learning research.

We analyse a specific instance of the general approach of reasoning based on forgetting by Lang and Marquis. More precisely, we discuss an approach for reasoning with inconsistent information using maximal consistent subsignatures, where a maximal consistent subsignature is a maximal set of propositions such that forgetting the remaining propositions restores consistency. We analyse maximal consistent subsignatures and the corresponding minimal inconsistent subsignatures in-depth and show, among others, that the hitting set duality applies for them as well. We further analyse inference relations based on maximal consistent subsignatures wrt. rationality postulates from non-monotonic reasoning and computational complexity. We also consider the relationship of our approach with inconsistency measurement and paraconsistent reasoning.

Vision-language models (VLMs) excel at tasks requiring joint understanding of visual and linguistic information. A particularly promising yet under-explored application for these models lies in answering questions based on various kinds of maps. This study investigates the efficacy of VLMs in answering questions based on choropleth maps, which are widely used for data analysis and representation. To facilitate and encourage research in this area, we introduce a novel map-based question-answering benchmark, consisting of maps from three geographical regions (United States, India, China), each containing 1000 questions. Our benchmark incorporates 43 diverse question templates, requiring nuanced understanding of relative spatial relationships, intricate map features, and complex reasoning. It also includes maps with discrete and continuous values, encompassing variations in color-mapping, category ordering, and stylistic patterns, enabling comprehensive analysis. We evaluate the performance of multiple VLMs on this benchmark, highlighting gaps in their abilities and providing insights for improving such models.

We apply a state-of-the-art difference-in-differences approach to estimate the impact of ChatGPT's release on the writing style of condensed matter papers on arXiv. Our analysis reveals a statistically significant improvement in the English quality of abstracts written by non-native English speakers. Importantly, this improvement remains robust even after accounting for other potential factors, confirming that it can be attributed to the release of ChatGPT. This indicates widespread adoption of the tool. Following the release of ChatGPT, there is a significant increase in the use of unique words, while the frequency of rare words decreases. Across language families, the changes in writing style are significant for authors from the Latin and Ural-Altaic groups, but not for those from the Germanic or other Indo-European groups.

Deep Reinforcement Learning (DRL) is a frequently employed technique to solve scheduling problems. Although DRL agents ace at delivering viable results in short computing times, their reasoning remains opaque. We conduct a case study where we systematically apply two explainable AI (xAI) frameworks, namely SHAP (DeepSHAP) and Captum (Input x Gradient), to describe the reasoning behind scheduling decisions of a specialized DRL agent in a flow production. We find that methods in the xAI literature lack falsifiability and consistent terminology, do not adequately consider domain-knowledge, the target audience or real-world scenarios, and typically provide simple input-output explanations rather than causal interpretations. To resolve this issue, we introduce a hypotheses-based workflow. This approach enables us to inspect whether explanations align with domain knowledge and match the reward hypotheses of the agent. We furthermore tackle the challenge of communicating these insights to third parties by tailoring hypotheses to the target audience, which can serve as interpretations of the agent's behavior after verification. Our proposed workflow emphasizes the repeated verification of explanations and may be applicable to various DRL-based scheduling use cases.