Misinformation regarding climate change is a key roadblock in addressing one of the most serious threats to humanity. This paper investigates factual accuracy in large language models (LLMs) regarding climate information. Using true/false labeled Q&A data for fine-tuning and evaluating LLMs on climate-related claims, we compare open-source models, assessing their ability to generate truthful responses to climate change questions. We investigate the detectability of models intentionally poisoned with false climate information, finding that such poisoning may not affect the accuracy of a model's responses in other domains. Furthermore, we compare the effectiveness of unlearning algorithms, fine-tuning, and Retrieval-Augmented Generation (RAG) for factually grounding LLMs on climate change topics. Our evaluation reveals that unlearning algorithms can be effective for nuanced conceptual claims, despite previous findings suggesting their inefficacy in privacy contexts. These insights aim to guide the development of more factually reliable LLMs and highlight the need for additional work to secure LLMs against misinformation attacks.

In deterministic optimization, adaptive stepsize strategies, such as line search (see [39], therein), AdaGrad-Norm [55], Polyak stepsize [46], and others were developed to provide stability and improve efficiency and adaptivity to unknown parameters. While the practical benefits for deterministic optimization problems are well-documented, much of our understanding of adaptive learning rate strategies for stochastic algorithms are still in their infancy. There are many adaptive learning rate strategies used in machine learning with many design goals. Some are known to adapt to SGD gradient noise while others are robust to hyper-parameters (e.g., [4, 59]). Theoretical results for adaptive algorithms tend to focus on guaranteeing minimax-optimal rates, but this theory is not engineered to provide realistic performance comparisons; indeed many adaptive algorithms are minimax-optimal, and so more precise statements are needed to distinguish them. For instance, the exact learning rates (or rate schedules) to which these strategies converge are unknown, nor their dependence on the geometry of the problem. Moreover, we often do not know how these adaptive stepsizes compare with well-tuned constant or decaying fixed learning rate stochastic gradient descent (SGD), which can be viewed as a cost associated with selecting the adaptive strategy in comparison to tuning by hand.

Deferring systems extend supervised Machine Learning (ML) models with the possibility to defer predictions to human experts. However, evaluating the impact of a deferring strategy on system accuracy is still an overlooked area. This paper fills this gap by evaluating deferring systems through a causal lens. We link the potential outcomes framework for causal inference with deferring systems. This allows us to identify the causal impact of the deferring strategy on predictive accuracy. We distinguish two scenarios. In the first one, we can access both the human and the ML model predictions for the deferred instances. In such a case, we can identify the individual causal effects for deferred instances and aggregates of them. In the second scenario, only human predictions are available for the deferred instances. In this case, we can resort to regression discontinuity design to estimate a local causal effect. We empirically evaluate our approach on synthetic and real datasets for seven deferring systems from the literature.

Moral judgement is a complex human reaction that engages cognitive and emotional dimensions. While some of the morality neural correlates are known, it is currently unclear if we can detect moral violation at a single-trial level. In a pilot study, here we explore the feasibility of moral judgement decoding from text stimuli with passive brain-computer interfaces. For effective moral judgement elicitation, we use video-audio affective priming prior to text stimuli presentation and attribute the text to moral agents. Our results show that further efforts are necessary to achieve reliable classification between moral congruency vs. incongruency states. We obtain good accuracy results for neutral vs. morally-charged trials. With this research, we try to pave the way towards neuroadaptive human-computer interaction and more human-compatible large language models (LLMs)

Retrieval Augmented Generation (RAG) has greatly improved the performance of Large Language Model (LLM) responses by grounding generation with context from existing documents. These systems work well when documents are clearly relevant to a question context. But what about when a document has partial information, or less obvious connections to the context? And how should we reason about connections between documents? In this work, we seek to answer these two core questions about RAG generation. We introduce G-RAG, a reranker based on graph neural networks (GNNs) between the retriever and reader in RAG. Our method combines both connections between documents and semantic information (via Abstract Meaning Representation graphs) to provide a context-informed ranker for RAG. G-RAG outperforms state-of-the-art approaches while having smaller computational footprint. Additionally, we assess the performance of PaLM 2 as a reranker and find it to significantly underperform G-RAG. This result emphasizes the importance of reranking for RAG even when using Large Language Models.

English verbs have multiple forms. For instance, talk may also appear as talks, talked or talking, depending on the context. The NLP task of lemmatization seeks to map these diverse forms back to a canonical one, known as the lemma. We present a simple joint neural model for lemmatization and morphological tagging that achieves state-of-the-art results on 20 languages from the Universal Dependencies corpora. Our paper describes the model in addition to training and decoding procedures. Error analysis indicates that joint morphological tagging and lemmatization is especially Figure 1: Our structured neural model shown as a hybrid helpful in low-resource lemmatization and languages (directed-undirected) graphical model (Koller and that display a larger degree of morphological Friedman, 2009).

Deep learning foundation models are revolutionizing many facets of science by leveraging vast amounts of data to learn general-purpose representations that can be adapted to tackle diverse downstream tasks. Foundation models hold the promise to also transform our ability to model our planet and its subsystems by exploiting the vast expanse of Earth system data. Here we introduce Aurora, a large-scale foundation model of the atmosphere trained on over a million hours of diverse weather and climate data. Aurora leverages the strengths of the foundation modelling approach to produce operational forecasts for a wide variety of atmospheric prediction problems, including those with limited training data, heterogeneous variables, and extreme events. In under a minute, Aurora produces 5-day global air pollution predictions and 10-day high-resolution weather forecasts that outperform state-of-the-art classical simulation tools and the best specialized deep learning models. Taken together, these results indicate that foundation models can transform environmental forecasting.

We present an expectation-maximization (EM) based unified framework for non-negative tensor decomposition that optimizes the Kullback-Leibler divergence. To avoid iterations in each M-step and learning rate tuning, we establish a general relationship between low-rank decomposition and many-body approximation. Using this connection, we exploit that the closed-form solution of the many-body approximation can be used to update all parameters simultaneously in the M-step. Our framework not only offers a unified methodology for a variety of low-rank structures, including CP, Tucker, and Train decompositions, but also their combinations forming mixtures of tensors as well as robust adaptive noise modeling. Empirically, we demonstrate that our framework provides superior generalization for discrete density estimation compared to conventional tensor-based approaches.

Experts in various fields routinely perform methodical writing tasks to plan, organize, and report their work. From a clinician writing a differential diagnosis for a patient, to a teacher writing a lesson plan for students, these tasks are pervasive, requiring to methodically generate structured long-form output for a given input. We develop a typology of methodical tasks structured in the form of a task objective, procedure, input, and output, and introduce DoLoMiTes, a novel benchmark with specifications for 519 such tasks elicited from hundreds of experts from across 25 fields. Our benchmark further contains specific instantiations of methodical tasks with concrete input and output examples (1,857 in total) which we obtain by collecting expert revisions of up to 10 model-generated examples of each task. We use these examples to evaluate contemporary language models highlighting that automating methodical tasks is a challenging long-form generation problem, as it requires performing complex inferences, while drawing upon the given context as well as domain knowledge.

In this work, we propose a novel method named \textbf{Auto}mated Process Labeling via \textbf{C}onfidence \textbf{V}ariation (\textbf{\textsc{AutoCV}}) to enhance the reasoning capabilities of large language models (LLMs) by automatically annotating the reasoning steps. Our approach begins by training a verification model on the correctness of final answers, enabling it to generate automatic process annotations. This verification model assigns a confidence score to each reasoning step, indicating the probability of arriving at the correct final answer from that point onward. We detect relative changes in the verification's confidence scores across reasoning steps to automatically annotate the reasoning process. This alleviates the need for numerous manual annotations or the high computational costs associated with model-induced annotation approaches. We experimentally validate that the confidence variations learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps. Subsequently, we demonstrate that the process annotations generated by \textsc{AutoCV} can improve the accuracy of the verification model in selecting the correct answer from multiple outputs generated by LLMs. Notably, we achieve substantial improvements across five datasets in mathematics and commonsense reasoning. The source code of \textsc{AutoCV} is available at \url{https://github.com/rookie-joe/AUTOCV}.