相关论文: Metadata Might Make Language Models Better

When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…

We consider the task of word-level language modeling and study the possibility of combining hidden-states-based short-term representations with medium-term representations encoded in dynamical weights of a language model. Our work extends…

This study evaluates the forecasting performance of recent language models (LLMs) on binary forecasting questions. We first introduce a novel dataset of over 600 binary forecasting questions, augmented with related news articles and their…

Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historical-value models. Yet, despite the attractive properties of time-index models, such as being able to…

Keeping the performance of language technologies optimal as time passes is of great practical interest. We study temporal effects on model performance on downstream language tasks, establishing a nuanced terminology for such discussion and…

Large-scale pretrained models using self-supervised learning have reportedly improved the performance of speech anti-spoofing. However, the attacker side may also make use of such models. Also, since it is very expensive to train such…

Despite impressive success, language models often generate outputs with flawed linguistic structure. We analyze the effect of directly infusing various kinds of syntactic and semantic information into large language models. To demonstrate…

The academic literature of social sciences records human civilization and studies human social problems. With its large-scale growth, the ways to quickly find existing research on relevant issues have become an urgent demand for…

It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take…

Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore this information. While specialized models have been…

Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this…

Closed-book question-answering (QA) is a challenging task that requires a model to directly answer questions without access to external knowledge. It has been shown that directly fine-tuning pre-trained language models with (question,…

Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However,…

Topic modelling, as a well-established unsupervised technique, has found extensive use in automatically detecting significant topics within a corpus of documents. However, classic topic modelling approaches (e.g., LDA) have certain…

This study evaluates large language models as estimable classifiers and clarifies how modeling choices shape downstream measurement error. Revisiting the Economic Policy Uncertainty index, we show that contemporary classifiers substantially…

Evidence plays a crucial role in automated fact-checking. When verifying real-world claims, existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. Such methods…

Effective training of deep neural networks can be challenging, and there remain many open questions on how to best learn these models. Recently developed methods to improve neural network training examine teaching: providing learned…

Predicting how Congressional legislators will vote is important for understanding their past and future behavior. However, previous work on roll-call prediction has been limited to single session settings, thus did not consider…

Learning word embeddings using distributional information is a task that has been studied by many researchers, and a lot of studies are reported in the literature. On the contrary, less studies were done for the case of multiple languages.…

As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with…