Urban Building Energy Modeling (UBEM) is an emerging method to investigate urban design and energy systems against the increasing energy demand at urban and neighborhood levels. However, current UBEM methods are mostly physic-based and time-consuming in multiple climate change scenarios. This work proposes CityTFT, a data-driven UBEM framework, to accurately model the energy demands in urban environments. With the empowerment of the underlying TFT framework and an augmented loss function, CityTFT could predict heating and cooling triggers in unseen climate dynamics with an F1 score of 99.98 \% while RMSE of loads of 13.57 kWh.

Time series forecasting is a subject of significant scientific and industrial importance. Despite the widespread utilization of forecasting methods, there is a dearth of research aimed at comprehending the conditions under which these methods yield favorable or unfavorable performances. Empirical studies, although common, encounter challenges due to the limited availability of datasets, impeding the extraction of reliable insights. To address this, we present tsMorph, a straightforward approach for generating semi-synthetic time series through dataset morphing. tsMorph operates by creating a sequence of datasets derived from two original datasets. These newly generated datasets exhibit a progressive departure from the characteristics of one dataset and a convergence toward the attributes of the other. This method provides a valuable alternative for obtaining substantial datasets. In this paper, we demonstrate the utility of tsMorph by assessing the performance of the Long Short-Term Memory Network forecasting algorithm. The time series under examination are sourced from the NN5 Competition. The findings reveal compelling insights. Notably, the performance of the Long Short-Term Memory Network improves proportionally with the frequency of the time series. These experiments affirm that tsMorph serves as an effective tool for gaining an understanding of forecasting algorithm behaviors, offering a pathway to overcome the limitations posed by empirical studies and enabling more extensive and reliable experimentation.

Diffusion probabilistic models (DPMs) have exhibited exceptional proficiency in generating visual media of outstanding quality and realism. Nonetheless, their potential in non-generative domains, such as face recognition, has yet to be thoroughly investigated. Meanwhile, despite the extensive development of multi-modal face recognition methods, their emphasis has predominantly centered on visual modalities. In this context, face recognition through textual description presents a unique and promising solution that not only transcends the limitations from application scenarios but also expands the potential for research in the field of cross-modal face recognition. It is regrettable that this avenue remains unexplored and underutilized, a consequence from the challenges mainly associated with three aspects: 1) the intrinsic imprecision of verbal descriptions; 2) the significant gaps between texts and images; and 3) the immense hurdle posed by insufficient databases.To tackle this problem, we present DiFace, a solution that effectively achieves face recognition via text through a controllable diffusion process, by establishing its theoretical connection with probability transport. Our approach not only unleashes the potential of DPMs across a broader spectrum of tasks but also achieves, to the best of our knowledge, a significant accuracy in text-to-image face recognition for the first time, as demonstrated by our experiments on verification and identification.

Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with language models, the goal of being evaluated as truthful). There are a number of existing definitions of deception in the literature on game theory and symbolic AI, but there is no overarching theory of deception for learning agents in games. We introduce a formal definition of deception in structural causal games, grounded in the philosophy literature, and applicable to real-world machine learning systems. Several examples and results illustrate that our formal definition aligns with the philosophical and commonsense meaning of deception. Our main technical result is to provide graphical criteria for deception. We show, experimentally, that these results can be used to mitigate deception in reinforcement learning agents and language models.

Translations help people understand content written in another language. However, even correct literal translations do not fulfill that goal when people lack the necessary background to understand them. Professional translators incorporate explicitations to explain the missing context by considering cultural differences between source and target audiences. Despite its potential to help users, NLP research on explicitation is limited because of the dearth of adequate evaluation methods. This work introduces techniques for automatically generating explicitations, motivated by WikiExpl: a dataset that we collect from Wikipedia and annotate with human translators. The resulting explicitations are useful as they help answer questions more accurately in a multilingual question answering framework.

Recent language models generate false but plausible-sounding text with surprising frequency. Such "hallucinations" are an obstacle to the usability of language-based AI systems and can harm people who rely upon their outputs. This work shows shows that there is an inherent statistical lower-bound on the rate that pretrained language models hallucinate certain types of facts, having nothing to do with the transformer LM architecture or data quality. For "arbitrary" facts whose veracity cannot be determined from the training data, we show that hallucinations must occur at a certain rate for language models that satisfy a statistical calibration condition appropriate for generative language models. Specifically, if the maximum probability of any fact is bounded, we show that the probability of generating a hallucination is close to the fraction of facts that occur exactly once in the training data (a "Good-Turing" estimate), even assuming ideal training data without errors. One conclusion is that models pretrained to be sufficiently good predictors (i.e., calibrated) may require post-training to mitigate hallucinations on the type of arbitrary facts that tend to appear once in the training set. However, our analysis also suggests that there is no statistical reason that pretraining will lead to hallucination on facts that tend to appear more than once in the training data (like references to publications such as articles and books, whose hallucinations have been particularly notable and problematic) or on systematic facts (like arithmetic calculations). Therefore, different architectures and learning algorithms may mitigate these latter types of hallucinations.

Search and planning algorithms have been a cornerstone of artificial intelligence since the field's inception. Giving reinforcement learning agents the ability to plan during execution time has resulted in significant performance improvements in various domains. However, in real-world environments, the model with respect to which the agent plans has been constrained to be grounded in the real environment itself, as opposed to a more abstract model which allows for planning over compound actions and behaviors. We propose a new method, called PiZero, that gives an agent the ability to plan in an abstract search space that the agent learns during training, which is completely decoupled from the real environment. Unlike prior approaches, this enables the agent to perform high-level planning at arbitrary timescales and reason in terms of compound or temporally-extended actions, which can be useful in environments where large numbers of base-level micro-actions are needed to perform relevant macro-actions. In addition, our method is more general than comparable prior methods because it seamlessly handles settings with continuous action spaces, combinatorial action spaces, and partial observability. We evaluate our method on multiple domains, including the traveling salesman problem, Sokoban, 2048, the facility location problem, and Pacman. Experimentally, it outperforms comparable prior methods without assuming access to an environment simulator at execution time.

Social media platforms such as Twitter (now known as X) have revolutionized how the public engage with important societal and political topics. Recently, climate change discussions on social media became a catalyst for political polarization and the spreading of misinformation. In this work, we aim to understand how real world events influence the opinions of individuals towards climate change related topics on social media. To this end, we extracted and analyzed a dataset of 13.6 millions tweets sent by 3.6 million users from 2006 to 2019. Then, we construct a temporal graph from the user-user mentions network and utilize the Louvain community detection algorithm to analyze the changes in community structure around Conference of the Parties on Climate Change~(COP) events. Next, we also apply tools from the Natural Language Processing literature to perform sentiment analysis and topic modeling on the tweets. Our work acts as a first step towards understanding the evolution of pro-climate change communities around COP events. Answering these questions helps us understand how to raise people's awareness towards climate change thus hopefully calling on more individuals to join the collaborative effort in slowing down climate change.

The remarkable abilities of large language models (LLMs) like GPT-4 partially stem from post-training processes like Reinforcement Learning from Human Feedback (RLHF) involving human preferences encoded in a reward model. However, these reward models (RMs) often lack direct knowledge of why, or under what principles, the preferences annotations were made. In this study, we identify principles that guide RMs to better align with human preferences, and then develop an axiomatic framework to generate a rich variety of preference signals to uphold them. We use these axiomatic signals to train a model for scoring answers to longform questions. Our approach yields a Preference Model with only about 220M parameters that agrees with gold human-annotated preference labels more often than GPT-4. The contributions of this work include: training a standalone preference model that can score human- and LLM-generated answers on the same scale; developing an axiomatic framework for generating training data pairs tailored to certain principles; and showing that a small amount of axiomatic signals can help small models outperform GPT-4 in preference scoring. We release our model on huggingface: https://huggingface.co/corbyrosset/axiomatic_preference_model

We provide a summary of the sixth edition of the CASE workshop that is held in the scope of RANLP 2023. The workshop consists of regular papers, three keynotes, working papers of shared task participants, and shared task overview papers. This workshop series has been bringing together all aspects of event information collection across technical and social science fields. In addition to contributing to the progress in text based event extraction, the workshop provides a space for the organization of a multimodal event information collection task.