Reasoning about time and temporal relations is an integral aspect of human cognition, essential for perceiving the world and navigating our experiences. Though large language models (LLMs) have demonstrated impressive performance in many reasoning tasks, temporal reasoning remains challenging due to its intrinsic complexity. In this work, we first study an essential task of temporal reasoning—temporal graph generation, to unveil LLMs’ inherent, global reasoning capabilities. We show that this task presents great challenges even for the most powerful LLMs, such as GPT-3.5/4. We also notice a significant performance gap by small models (< 10B) that lag behind LLMs by 50%. Next, we study how to close this gap with a budget constraint, e.g., not using model finetuning. We propose a new prompting technique tailored for temporal reasoning, Narrative-of-Thought (NoT), that first converts the events set to a Python class, then prompts a small model to generate a temporally grounded narrative, guiding the final generation of a temporal graph. Extensive experiments showcase the efficacy of NoT in improving various metrics. Notably, NoT attains the highest F1 on the Schema-11 evaluation set, while securing an overall F1 on par with GPT-3.5. NoT also achieves the best structural similarity across the board, even compared with GPT-3.5/4.

News media often strive to minimize explicit moral language in news articles, yet most articles are dense with moral values as expressed through the reported events themselves. However, values that are reflected in the intricate dynamics among *participating entities* and *moral events* are far more challenging for most NLP systems to detect, including LLMs. To study this phenomenon, we annotate a new dataset, **MORAL EVENTS**, consisting of 5,494 structured event annotations on 474 news articles by diverse US media across the political spectrum. We further propose **MOKA**, a moral event extraction framework with **MO**ral **K**nowledge **A**ugmentation, which leverages knowledge derived from moral words and moral scenarios to produce structural representations of morality-bearing events. Experiments show that **MOKA** outperforms competitive baselines across three moral event understanding tasks. Further analysis shows even ostensibly nonpartisan media engage in the selective reporting of moral events.

Public opinion is shaped by the information news media provide, and that information in turn may be shaped by the ideological preferences of media outlets. But while much attention has been devoted to media bias via overt ideological language or topic selection, a more unobtrusive way in which the media shape opinion is via the strategic inclusion or omission of partisan events that may support one side or the other. We develop a latent variable-based framework to predict the ideology of news articles by comparing multiple articles on the same story and identifying partisan events whose inclusion or omission reveals ideology. Our experiments first validate the existence of partisan event selection, and then show that article alignment and cross-document comparison detect partisan events and article ideology better than competitive baselines. Our results reveal the high-level form of media bias, which is present even among mainstream media with strong norms of objectivity and nonpartisanship. Our codebase and dataset are available at https://github.com/launchnlp/ATC.

News media is expected to uphold unbiased reporting. Yet they may still affect public opinion by selectively including or omitting events that support or contradict their ideological positions. Prior work in NLP has only studied media bias via linguistic style and word usage. In this paper, we study to which degree media balances news reporting and affects consumers through event inclusion or omission. We first introduce the task of detecting both partisan and counter-partisan events: events that support or oppose the author’s political ideology. To conduct our study, we annotate a high-quality dataset, PAC, containing 8,511 (counter-)partisan event annotations in 304 news articles from ideologically diverse media outlets. We benchmark PAC to highlight the challenges of this task. Our findings highlight both the ways in which the news subtly shapes opinion and the need for large language models that better understand events within a broader context. Our dataset can be found at https://github.com/launchnlp/Partisan-Event-Dataset.

Stance detection is typically framed as predicting the sentiment in a given text towards a target entity. However, this setup overlooks the importance of the source entity, i.e., who is expressing the opinion. In this paper, we emphasize the imperative need for studying interactions among entities when inferring stances. We first introduce a new task, entity-to-entity (E2E) stance detection, which primes models to identify entities in their canonical names and discern stances jointly. To support this study, we curate a new dataset with 10,641 annotations labeled at the sentence level from news articles of different ideological leanings. We present a novel generative framework to allow the generation of canonical names for entities as well as stances among them. We further enhance the model with a graph encoder to summarize entity activities and external knowledge surrounding the entities. Experiments show that our model outperforms strong comparisons by large margins. Further analyses demonstrate the usefulness of E2E stance detection for understanding media quotation and stance landscape as well as inferring entity ideology.

As polarization continues to rise among both the public and the news media, increasing attention has been devoted to detecting media bias. Most recent work in the NLP community, however, identify bias at the level of individual articles. However, each article itself comprises multiple sentences, which vary in their ideological bias. In this paper, we aim to identify sentences within an article that can illuminate and explain the overall bias of the entire article. We show that understanding the discourse role of a sentence in telling a news story, as well as its relation with nearby sentences, can reveal the ideological leanings of an author even when the sentence itself appears merely neutral. In particular, we consider using a functional news discourse structure and PDTB discourse relations to inform bias sentence identification, and distill the auxiliary knowledge from the two types of discourse structure into our bias sentence identification system. Experimental results on benchmark datasets show that incorporating both the global functional discourse structure and local rhetorical discourse relations can effectively increase the recall of bias sentence identification by 8.27% - 8.62%, as well as increase the precision by 2.82% - 3.48%.

Ideology is at the core of political science research. Yet, there still does not exist general-purpose tools to characterize and predict ideology across different genres of text. To this end, we study Pretrained Language Models using novel ideology-driven pretraining objectives that rely on the comparison of articles on the same story written by media of different ideologies. We further collect a large-scale dataset, consisting of more than 3.6M political news articles, for pretraining. Our model POLITICS outperforms strong baselines and the previous state-of-the-art models on ideology prediction and stance detection tasks. Further analyses show that POLITICS is especially good at understanding long or formally written texts, and is also robust in few-shot learning scenarios.

Debate and deliberation play essential roles in politics and government, but most models presume that debates are won mainly via superior style or agenda control. Ideally, however, debates would be won on the merits, as a function of which side has the stronger arguments. We propose a predictive model of debate that estimates the effects of linguistic features and the latent persuasive strengths of different topics, as well as the interactions between the two. Using a dataset of 118 Oxford-style debates, our model’s combination of content (as latent topics) and style (as linguistic features) allows us to predict audience-adjudicated winners with 74% accuracy, significantly outperforming linguistic features alone (66%). Our model finds that winning sides employ stronger arguments, and allows us to identify the linguistic features associated with strong or weak arguments.