News media employ moral language to create memorable stories, and readers often engage with the content that align with their values. Moral theories have been applied to news analysis studying moral values in isolation, while the intricate dynamics among participating entities in shaping moral events have been overlooked. This is mainly due to the use of obscure language to conceal evident ideology and values, coupled with the insufficient moral reasoning capability in most existing NLP systems, where LLMs are no exception. To study this phenomenon, we first annotate a new dataset, MORAL EVENTS, consisting of 5,494 structured annotations on 474 news articles by diverse US media across the political spectrum. We further propose MOKA, a moral event extraction framework with MOral Knowledge Augmentation, that leverages knowledge derived from moral words and moral scenarios. Experimental results show that MOKA outperforms competitive baselines across three moral event understanding tasks. Further analyses illuminate the selective reporting of moral events by media outlets of different ideological leanings, suggesting the significance of event-level morality analysis in news. Our datasets and codebase are available at https://github.com/launchnlp/MOKA.

Despite the recent advancement in large language models (LLMs) and their high performances across numerous benchmarks, recent research has unveiled that LLMs suffer from hallucinations and unfaithful reasoning. This work studies a specific type of hallucination induced by semantic associations. Specifically, we investigate to what extent LLMs take shortcuts from certain keyword/entity biases in the prompt instead of following the correct reasoning path. To quantify this phenomenon, we propose a novel probing method and benchmark called EureQA. We start from questions that LLMs will answer correctly with utmost certainty, and mask the important entity with evidence sentence recursively, asking models to find masked entities according to a chain of evidence before answering the question. During the construction of the evidence, we purposefully replace semantic clues (entities) that may lead to the correct answer with distractor clues (evidence) that will not directly lead to the correct answer but require a chain-like reasoning process. We evaluate if models can follow the correct reasoning chain instead of short-cutting through distractor clues. We find that existing LLMs lack the necessary capabilities to follow correct reasoning paths and resist the attempt of greedy shortcuts. We show that the distractor semantic associations often lead to model hallucination, which is strong evidence that questions the validity of current LLM reasoning.

Are the longstanding robustness issues in NLP resolved by today's larger and more performant models? To address this question, we conduct a thorough investigation using 19 models of different sizes spanning different architectural choices and pretraining objectives. We conduct evaluations using (a) OOD and challenge test sets, (b) CheckLists, (c) contrast sets, and (d) adversarial inputs. Our analysis reveals that not all OOD tests provide further insight into robustness. Evaluating with CheckLists and contrast sets shows significant gaps in model performance; merely scaling models does not make them sufficiently robust. Finally, we point out that current approaches for adversarial evaluations of models are themselves problematic: they can be easily thwarted, and in their current forms, do not represent a sufficiently deep probe of model robustness. We conclude that not only is the question of robustness in NLP as yet unresolved, but even some of the approaches to measure robustness need to be reassessed.

Susceptibility to misinformation describes the extent to believe unverifiable claims, which is hidden in people's mental process and infeasible to observe. Existing susceptibility studies heavily rely on the self-reported beliefs, making any downstream applications on susceptability hard to scale. To address these limitations, in this work, we propose a computational model to infer users' susceptibility levels given their activities. Since user's susceptibility is a key indicator for their reposting behavior, we utilize the supervision from the observable sharing behavior to infer the underlying susceptibility tendency. The evaluation shows that our model yields estimations that are highly aligned with human judgment on users' susceptibility level comparisons. Building upon such large-scale susceptibility labeling, we further conduct a comprehensive analysis of how different social factors relate to susceptibility. We find that political leanings and psychological factors are associated with susceptibility in varying degrees.

Accurately simulating human opinion dynamics is crucial for understanding a variety of societal phenomena, including polarization and the spread of misinformation. However, the agent-based models (ABMs) commonly used for such simulations lack fidelity to human behavior. We propose a new approach to simulating opinion dynamics based on populations of Large Language Models (LLMs). Our findings reveal a strong inherent bias in LLM agents towards accurate information, leading to consensus in line with scientific reality. However, this bias limits the simulation of individuals with resistant views on issues like climate change. After inducing confirmation bias through prompt engineering, we observed opinion fragmentation in line with existing agent-based research. These insights highlight the promise and limitations of LLM agents in this domain and suggest a path forward: refining LLMs with real-world discourse to better simulate the evolution of human beliefs.

In-context learning has been applied to knowledge-rich tasks such as question answering. In such scenarios, in-context examples are used to trigger a behaviour in the language model: namely, it should surface information stored in its parametric knowledge. We study the construction of in-context example sets, with a focus on the parametric knowledge of the model regarding in-context examples. We identify 'known' examples, where models can correctly answer from its parametric knowledge, and 'unknown' ones. Our experiments show that prompting with 'unknown' examples decreases the performance, potentially as it encourages hallucination rather than searching its parametric knowledge. Constructing an in-context example set that presents both known and unknown information performs the best across diverse settings. We perform analysis on three multi-answer question answering datasets, which allows us to further study answer set ordering strategies based on the LM's knowledge about each answer. Together, our study sheds lights on how to best construct in-context example sets for knowledge-rich tasks.

We consider the problem of sequential evaluation, in which an evaluator observes candidates in a sequence and assigns scores to these candidates in an online, irrevocable fashion. Motivated by the psychology literature that has studied sequential bias in such settings -- namely, dependencies between the evaluation outcome and the order in which the candidates appear -- we propose a natural model for the evaluator's rating process that captures the lack of calibration inherent to such a task. We conduct crowdsourcing experiments to demonstrate various facets of our model. We then proceed to study how to correct sequential bias under our model by posing this as a statistical inference problem. We propose a near-linear time, online algorithm for this task and prove guarantees in terms of two canonical ranking metrics. We also prove that our algorithm is information theoretically optimal, by establishing matching lower bounds in both metrics. Finally, we perform a host of numerical experiments to show that our algorithm often outperforms the de facto method of using the rankings induced by the reported scores, both in simulation and on the crowdsourcing data that we collected.

A restaurant in a rural Oregon city couldn't find enough servers to stay fully staffed. So the owner hired a robot named Plato. She had no idea how much pushback she'd get from the community. ROCKY ROAD: A hyped AI-based restaurant opened to fanfare last month in San Francisco. 'INCREDIBLY POOR DECISION': Biden hands China big win with military AI deal, experts say.

Technically speaking, neuroscientists have been able to read your mind for decades. First, you must lie motionless within a hulking fMRI scanner, perhaps for hours, while you watch films or listen to audiobooks. None of this, of course, can be done without your consent; for the foreseeable future, your thoughts will remain your own, if you so choose. But if you do elect to endure claustrophobic hours in the scanner, the software will learn to generate a bespoke reconstruction of what you were seeing or listening to, just by analyzing how blood moves through your brain. More recently, researchers have deployed generative AI tools, like Stable Diffusion and GPT, to create far more realistic, if not entirely accurate, reconstructions of films and podcasts based on neural activity. But as exciting as the idea of extracting a movie from someone's brain activity may be, it is a highly limited form of "mind reading."

Recognizing fallacies is crucial for ensuring the quality and validity of arguments across various domains. However, computational fallacy recognition faces challenges due to the diverse genres, domains, and types of fallacies found in datasets. This leads to a highly multiclass, and even multi-label, setup with substantial class imbalance. In this study, we aim to enhance existing models for fallacy recognition by incorporating additional context and by leveraging large language models to generate synthetic data, thus increasing the representation of the infrequent classes. We experiment with GPT3.5 to generate synthetic examples and we examine the impact of prompt settings for this. Moreover, we explore zero-shot and few-shot scenarios to evaluate the effectiveness of using the generated examples for training smaller models within a unified fallacy recognition framework. Furthermore, we analyze the overlap between the synthetic data and existing fallacy datasets. Finally, we investigate the usefulness of providing supplementary context for detecting fallacy types that need such context, e.g., diversion fallacies. Our evaluation results demonstrate consistent improvements across fallacy types, datasets, and generators.