Are Large Language Models (LLMs) temporally grounded? Since LLMs cannot perceive and interact with the environment, it is impossible to answer this question directly. Instead, we provide LLMs with textual narratives and probe them with respect to their common-sense knowledge of the structure and duration of events, their ability to order events along a timeline, and self-consistency within their temporal model (e.g., temporal relations such as after and before are mutually exclusive for any pair of events). We evaluate state-of-the-art LLMs (such as LLaMA 2 and GPT-4) on three tasks reflecting these abilities. Generally, we find that LLMs lag significantly behind both human performance as well as small-scale, specialised LMs. In-context learning, instruction tuning, and chain-of-thought prompting reduce this gap only to a limited degree. Crucially, LLMs struggle the most with self-consistency, displaying incoherent behaviour in at least 27.23% of their predictions. Contrary to expectations, we also find that scaling the model size does not guarantee positive gains in performance. To explain these results, we study the sources from which LLMs may gather temporal information: we find that sentence ordering in unlabelled texts, available during pre-training, is only weakly correlated with event ordering. Moreover, public instruction tuning mixtures contain few temporal tasks. Hence, we conclude that current LLMs lack a consistent temporal model of textual narratives.

Hallucinations pose a significant challenge to the reliability of neural models for abstractive summarisation. While automatically generated summaries may be fluent, they often lack faithfulness to the original document. This issue becomes even more pronounced in low-resource languages, where summarisation requires cross-lingual transfer. With the existing faithful metrics focusing on English, even measuring the extent of this phenomenon in cross-lingual settings is hard. To address this, we first develop a novel metric, mFACT, evaluating the faithfulness of non-English summaries, leveraging translation-based transfer from multiple English faithfulness metrics. Through extensive experiments in multiple languages, we demonstrate that mFACT is best suited to detect hallucinations compared to alternative metrics. With mFACT, we assess a broad range of multilingual large language models, and find that they all tend to hallucinate often in languages different from English. We then propose a simple but effective method to reduce hallucinations in cross-lingual transfer, which weighs the loss of each training example by its faithfulness score. This method drastically increases both performance and faithfulness according to both automatic and human evaluation when compared to strong baselines for cross-lingual transfer such as MAD-X. Our code and dataset are available at https://github.com/yfqiu-nlp/mfact-summ.

We present the Assignment-Maximization Spectral Attribute removaL (AMSAL) algorithm, which erases information from neural representations when the information to be erased is implicit rather than directly being aligned to each input example. Our algorithm works by alternating between two steps. In one, it finds an assignment of the input representations to the information to be erased, and in the other, it creates projections of both the input representations and the information to be erased into a joint latent space. We test our algorithm on an extensive array of datasets, including a Twitter dataset with multiple guarded attributes, the BiasBios dataset, and the BiasBench benchmark. The latter benchmark includes four datasets with various types of protected attributes. Our results demonstrate that bias can often be removed in our setup. We also discuss the limitations of our approach when there is a strong entanglement between the main task and the information to be erased.1

We present an analysis tool based on joint matrix factorization for comparing latent representations of multilingual and monolingual models. An alternative to probing, this tool allows us to analyze multiple sets of representations in a joint manner. Using this tool, we study to what extent and how morphosyntactic features are reflected in the representations learned by multilingual pre-trained models. We conduct a large-scale empirical study of over 33 languages and 17 morphosyntactic categories. Our findings demonstrate variations in the encoding of morphosyntactic information across upper and lower layers, with category-specific differences influenced by language properties. Hierarchical clustering of the factorization outputs yields a tree structure that is related to phylogenetic trees manually crafted by linguists. Moreover, we find the factorization outputs exhibit strong associations with performance observed across different cross-lingual tasks. We release our code to facilitate future research.

We describe a simple and effective method (Spectral Attribute removaL; SAL) to remove private or guarded information from neural representations. Our method uses matrix decomposition to project the input representations into directions with reduced covariance with the guarded information rather than maximal covariance as factorization methods normally use. We begin with linear information removal and proceed to generalize our algorithm to the case of nonlinear information removal using kernels. Our experiments demonstrate that our algorithm retains better main task performance after removing the guarded information compared to previous work. In addition, our experiments demonstrate that we need a relatively small amount of guarded attribute data to remove information about these attributes, which lowers the exposure to sensitive data and is more suitable for low-resource scenarios.

We introduce a task consisting in matching a proof to a given mathematical statement. The task fits well within current research on Mathematical Information Retrieval and, more generally, mathematical article analysis (Mathematical Sciences, 2014). We present a dataset for the task (the MATcH dataset) consisting of over 180k statement-proof pairs extracted from modern mathematical research articles. We find this dataset highly representative of our task, as it consists of relatively new findings useful to mathematicians. We propose a bilinear similarity model and two decoding methods to match statements to proofs effectively. While the first decoding method matches a proof to a statement without being aware of other statements or proofs, the second method treats the task as a global matching problem. Through a symbol replacement procedure, we analyze the “insights” that pre-trained language models have in such mathematical article analysis and show that while these models perform well on this task with the best performing mean reciprocal rank of 73.7, they follow a relatively shallow symbolic analysis and matching to achieve that performance.

We argue that disentangling content selection from the budget used to cover salient content improves the performance and applicability of abstractive summarizers. Our method, FactorSum, does this disentanglement by factorizing summarization into two steps through an energy function: (1) generation of abstractive summary views covering salient information in subsets of the input document (document views); (2) combination of these views into a final summary, following a budget and content guidance. This guidance may come from different sources, including from an advisor model such as BART or BigBird, or in oracle mode – from the reference. This factorization achieves significantly higher ROUGE scores on multiple benchmarks for long document summarization, namely PubMed, arXiv, and GovReport. Most notably, our model is effective for domain adaptation. When trained only on PubMed samples, it achieves a 46.29 ROUGE-1 score on arXiv, outperforming PEGASUS trained in domain by a large margin. Our experimental results indicate that the performance gains are due to more flexible budget adaptation and processing of shorter contexts provided by partial document views.

We investigate how different domains are encoded in modern neural network architectures. We analyze the relationship between natural language domains, model size, and the amount of training data used. The primary analysis tool we develop is based on subpopulation analysis with Singular Vector Canonical Correlation Analysis (SVCCA), which we apply to Transformer-based language models (LMs). We compare the latent representations of such a language model at its different layers from a pair of models: a model trained on multiple domains (an experimental model) and a model trained on a single domain (a control model). Through our method, we find that increasing the model capacity impacts how domain information is stored in upper and lower layers differently. In addition, we show that larger experimental models simultaneously embed domain-specific information as if they were conjoined control models. These findings are confirmed qualitatively, demonstrating the validity of our method.

Recent works made significant advances on summarization tasks, facilitated by summarization datasets. Several existing datasets have the form of coherent-paragraph summaries. However, these datasets were curated from academic documents that were written for experts, thus making the essential step of assessing the summarization output through human-evaluation very demanding. To overcome these limitations, we present a dataset based on article summaries appearing on the WikiHow website, composed of how-to articles and coherent-paragraph summaries written in plain language. We compare our dataset attributes to existing ones, including readability and world-knowledge, showing our dataset makes human evaluation significantly easier and thus, more effective. A human evaluation conducted on PubMed and the proposed dataset reinforces our findings.

Predicting the answer to a product-related question is an emerging field of research that recently attracted a lot of attention. Answering subjective and opinion-based questions is most challenging due to the dependency on customer generated content. Previous works mostly focused on review-aware answer prediction; however, these approaches fail for new or unpopular products, having no (or only a few) reviews at hand. In this work, we propose a novel and complementary approach for predicting the answer for such questions, based on the answers for similar questions asked on similar products. We measure the contextual similarity between products based on the answers they provide for the same question. A mixture-of-expert framework is used to predict the answer by aggregating the answers from contextually similar products. Empirical results demonstrate that our model outperforms strong baselines on some segments of questions, namely those that have roughly ten or more similar resolved questions in the corpus. We additionally publish two large-scale datasets used in this work, one is of similar product question pairs, and the second is of product question-answer pairs.

The rise of pre-trained language models has yielded substantial progress in the vast majority of Natural Language Processing (NLP) tasks. However, a generic approach towards the pre-training procedure can naturally be sub-optimal in some cases. Particularly, fine-tuning a pre-trained language model on a source domain and then applying it to a different target domain, results in a sharp performance decline of the eventual classifier for many source-target domain pairs. Moreover, in some NLP tasks, the output categories substantially differ between domains, making adaptation even more challenging. This, for example, happens in the task of aspect extraction, where the aspects of interest of reviews of, e.g., restaurants or electronic devices may be very different. This paper presents a new fine-tuning scheme for BERT, which aims to address the above challenges. We name this scheme DILBERT: Domain Invariant Learning with BERT, and customize it for aspect extraction in the unsupervised domain adaptation setting. DILBERT harnesses the categorical information of both the source and the target domains to guide the pre-training process towards a more domain and category invariant representation, thus closing the gap between the domains. We show that DILBERT yields substantial improvements over state-of-the-art baselines while using a fraction of the unlabeled data, particularly in more challenging domain adaptation setups.

Pivot Based Language Modeling (PBLM) (Ziser and Reichart, 2018a), combining LSTMs with pivot-based methods, has yielded significant progress in unsupervised domain adaptation. However, this approach is still challenged by the large pivot detection problem that should be solved, and by the inherent instability of LSTMs. In this paper we propose a Task Refinement Learning (TRL) approach, in order to solve these problems. Our algorithms iteratively train the PBLM model, gradually increasing the information exposed about each pivot. TRL-PBLM achieves stateof- the-art accuracy in six domain adaptation setups for sentiment classification. Moreover, it is much more stable than plain PBLM across model configurations, making the model much better fitted for practical use.

Representation learning with pivot-based methods and with Neural Networks (NNs) have lead to significant progress in domain adaptation for Natural Language Processing. However, most previous work that follows these approaches does not explicitly exploit the structure of the input text, and its output is most often a single representation vector for the entire text. In this paper we present the Pivot Based Language Model (PBLM), a representation learning model that marries together pivot-based and NN modeling in a structure aware manner. Particularly, our model processes the information in the text with a sequential NN (LSTM) and its output consists of a representation vector for every input word. Unlike most previous representation learning models in domain adaptation, PBLM can naturally feed structure aware text classifiers such as LSTM and CNN. We experiment with the task of cross-domain sentiment classification on 20 domain pairs and show substantial improvements over strong baselines.

While cross-domain and cross-language transfer have long been prominent topics in NLP research, their combination has hardly been explored. In this work we consider this problem, and propose a framework that builds on pivot-based learning, structure-aware Deep Neural Networks (particularly LSTMs and CNNs) and bilingual word embeddings, with the goal of training a model on labeled data from one (language, domain) pair so that it can be effectively applied to another (language, domain) pair. We consider two setups, differing with respect to the unlabeled data available for model training. In the full setup the model has access to unlabeled data from both pairs, while in the lazy setup, which is more realistic for truly resource-poor languages, unlabeled data is available for both domains but only for the source language. We design our model for the lazy setup so that for a given target domain, it can train once on the source language and then be applied to any target language without re-training. In experiments with nine English-German and nine English-French domain pairs our best model substantially outperforms previous models even when it is trained in the lazy setup and previous models are trained in the full setup.

We introduce a neural network model that marries together ideas from two prominent strands of research on domain adaptation through representation learning: structural correspondence learning (SCL, (Blitzer et al., 2006)) and autoencoder neural networks (NNs). Our model is a three-layer NN that learns to encode the non-pivot features of an input example into a low dimensional representation, so that the existence of pivot features (features that are prominent in both domains and convey useful information for the NLP task) in the example can be decoded from that representation. The low-dimensional representation is then employed in a learning algorithm for the task. Moreover, we show how to inject pre-trained word embeddings into our model in order to improve generalization across examples with similar pivot features. We experiment with the task of cross-domain sentiment classification on 16 domain pairs and show substantial improvements over strong baselines.