arXiv subjects

Fred Morstatter

Publications and source records attributed to Fred Morstatter.

At least 37 records · Page 2Linked to original sources

arXiv2024

Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias

Content moderation on social media platforms shapes the dynamics of online discourse, influencing whose voices are amplified and whose are suppressed. Recent studies have raised concerns about the fairness of content moderation practices, particularly for aggressively flagging posts from transgender and non-binary individuals as toxic. In this study, we investigate the presence of bias in harmful speech classification of gender-queer dialect online, focusing specifically on the treatment of reclaimed slurs. We introduce a novel dataset, QueerReclaimLex, based on 109 curated templates exemplifying non-derogatory uses of LGBTQ+ slurs. Dataset instances are scored by gender-queer annotators for potential harm depending on additional context about speaker identity. We systematically evaluate the performance of five off-the-shelf language models in assessing the harm of these texts and explore the effectiveness of chain-of-thought prompting to teach large language models (LLMs) to leverage author identity context. We reveal a tendency for these models to inaccurately flag texts authored by gender-queer individuals as harmful. Strikingly, across all LLMs the performance is poorest for texts that show signs of being written by individuals targeted by the featured slur (F1 <= 0.24). We highlight an urgent need for fairness and inclusivity in content moderation systems. By uncovering these biases, this work aims to inform the development of more equitable content moderation practices and contribute to the creation of inclusive online spaces for all users.

cs.CL↗

arXiv2024

Contextualizing Argument Quality Assessment with Relevant Knowledge

Automatic assessment of the quality of arguments has been recognized as a challenging task with significant implications for misinformation and targeted speech. While real-world arguments are tightly anchored in context, existing computational methods analyze their quality in isolation, which affects their accuracy and generalizability. We propose SPARK: a novel method for scoring argument quality based on contextualization via relevant knowledge. We devise four augmentations that leverage large language models to provide feedback, infer hidden assumptions, supply a similar-quality argument, or give a counter-argument. SPARK uses a dual-encoder Transformer architecture to enable the original argument and its augmentation to be considered jointly. Our experiments in both in-domain and zero-shot setups show that SPARK consistently outperforms existing techniques across multiple metrics.

cs.CL↗

arXiv2024

OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control

In the evolving landscape of text-to-3D technology, Dreamfusion has showcased its proficiency by utilizing Score Distillation Sampling (SDS) to optimize implicit representations such as NeRF. This process is achieved through the distillation of pretrained large-scale text-to-image diffusion models. However, Dreamfusion encounters fidelity and efficiency constraints: it faces the multi-head Janus issue and exhibits a relatively slow optimization process. To circumvent these challenges, we introduce OrientDream, a camera orientation conditioned framework designed for efficient and multi-view consistent 3D generation from textual prompts. Our strategy emphasizes the implementation of an explicit camera orientation conditioned feature in the pre-training of a 2D text-to-image diffusion module. This feature effectively utilizes data from MVImgNet, an extensive external multi-view dataset, to refine and bolster its functionality. Subsequently, we utilize the pre-conditioned 2D images as a basis for optimizing a randomly initialized implicit representation (NeRF). This process is significantly expedited by a decoupled back-propagation technique, allowing for multiple updates of implicit parameters per optimization cycle. Our experiments reveal that our method not only produces high-quality NeRF models with consistent multi-view properties but also achieves an optimization speed significantly greater than existing methods, as quantified by comparative metrics.

cs.CV↗

arXiv2024

Online network topology shapes personal narratives and hashtag generation

While narratives have shaped cognition and cultures for centuries, digital media and online social networks have introduced new narrative phenomena. With increased narrative agency, networked groups of individuals can directly contribute and steer narratives that center our collective discussions of politics, science, and morality. We report the results of an online network experiment on narrative and hashtag generation, in which networked groups of participants interpreted a text-based narrative of a disaster event, and were incentivized to produce matching hashtags with their network neighbors. We found that network structure not only influences the emergence of dominant beliefs through coordination with network neighbors, but also impacts participants' use of causal language in their personal narratives.

cs.SI↗

arXiv2024

Capturing Perspectives of Crowdsourced Annotators in Subjective Learning Tasks

Supervised classification heavily depends on datasets annotated by humans. However, in subjective tasks such as toxicity classification, these annotations often exhibit low agreement among raters. Annotations have commonly been aggregated by employing methods like majority voting to determine a single ground truth label. In subjective tasks, aggregating labels will result in biased labeling and, consequently, biased models that can overlook minority opinions. Previous studies have shed light on the pitfalls of label aggregation and have introduced a handful of practical approaches to tackle this issue. Recently proposed multi-annotator models, which predict labels individually per annotator, are vulnerable to under-determination for annotators with few samples. This problem is exacerbated in crowdsourced datasets. In this work, we propose \textbf{Annotator Aware Representations for Texts (AART)} for subjective classification tasks. Our approach involves learning representations of annotators, allowing for exploration of annotation behaviors. We show the improvement of our method on metrics that assess the performance on capturing individual annotators' perspectives. Additionally, we demonstrate fairness metrics to evaluate our model's equability of performance for marginalized annotators compared to others.

cs.CL↗

arXiv2024

Secret Keepers: The Impact of LLMs on Linguistic Markers of Personal Traits

Prior research has established associations between individuals' language usage and their personal traits; our linguistic patterns reveal information about our personalities, emotional states, and beliefs. However, with the increasing adoption of Large Language Models (LLMs) as writing assistants in everyday writing, a critical question emerges: are authors' linguistic patterns still predictive of their personal traits when LLMs are involved in the writing process? We investigate the impact of LLMs on the linguistic markers of demographic and psychological traits, specifically examining three LLMs - GPT3.5, Llama 2, and Gemini - across six different traits: gender, age, political affiliation, personality, empathy, and morality. Our findings indicate that although the use of LLMs slightly reduces the predictive power of linguistic patterns over authors' personal traits, the significant changes are infrequent, and the use of LLMs does not fully diminish the predictive power of authors' linguistic patterns over their personal traits. We also note that some theoretically established lexical-based linguistic markers lose their reliability as predictors when LLMs are used in the writing process. Our findings have important implications for the study of linguistic markers of personal traits in the age of LLMs.

cs.CL↗

arXiv2024

The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance

Large Language Models (LLMs) are regularly being used to label data across many domains and for myriad tasks. By simply asking the LLM for an answer, or ``prompting,'' practitioners are able to use LLMs to quickly get a response for an arbitrary task. This prompting is done through a series of decisions by the practitioner, from simple wording of the prompt, to requesting the output in a certain data format, to jailbreaking in the case of prompts that address more sensitive topics. In this work, we ask: do variations in the way a prompt is constructed change the ultimate decision of the LLM? We answer this using a series of prompt variations across a variety of text classification tasks. We find that even the smallest of perturbations, such as adding a space at the end of a prompt, can cause the LLM to change its answer. Further, we find that requesting responses in XML and commonly used jailbreaks can have cataclysmic effects on the data labeled by LLMs.

cs.CL↗

arXiv2024

Measuring Online Emotional Reactions to Events

The rich and dynamic information environment of social media provides researchers, policy makers, and entrepreneurs with opportunities to learn about social phenomena in a timely manner. However, using this data to understand social behavior is difficult due heterogeneity of topics and events discussed in the highly dynamic online information environment. To address these challenges, we present a method for systematically detecting and measuring emotional reactions to offline events using change point detection on the time series of collective affect, and further explaining these reactions using a transformer-based topic model. We demonstrate the utility of the method on a corpus of tweets from a large US metropolitan area between January and August, 2020, covering a period of great social change. We demonstrate that our method is able to disaggregate topics to measure population's emotional and moral reactions. This capability allows for better monitoring of population's reactions during crises using online data.

cs.SI↗

arXiv2024

Risk and Response in Large Language Models: Evaluating Key Threat Categories

This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align with human values, perceive and categorize different types of risks, we delve into the challenges posed by the subjective nature of preference-based training data. By utilizing the Anthropic Red-team dataset, we analyze major risk categories, including Information Hazards, Malicious Uses, and Discrimination/Hateful content. Our findings indicate that LLMs tend to consider Information Hazards less harmful, a finding confirmed by a specially developed regression model. Additionally, our analysis shows that LLMs respond less stringently to Information Hazards compared to other risks. The study further reveals a significant vulnerability of LLMs to jailbreaking attacks in Information Hazard scenarios, highlighting a critical security concern in LLM risk assessment and emphasizing the need for improved AI safety measures.

cs.CL↗

arXiv2024

Don't Blame the Data, Blame the Model: Understanding Noise and Bias When Learning from Subjective Annotations

Researchers have raised awareness about the harms of aggregating labels especially in subjective tasks that naturally contain disagreements among human annotators. In this work we show that models that are only provided aggregated labels show low confidence on high-disagreement data instances. While previous studies consider such instances as mislabeled, we argue that the reason the high-disagreement text instances have been hard-to-learn is that the conventional aggregated models underperform in extracting useful signals from subjective tasks. Inspired by recent studies demonstrating the effectiveness of learning from raw annotations, we investigate classifying using Multiple Ground Truth (Multi-GT) approaches. Our experiments show an improvement of confidence for the high-disagreement instances.

cs.CL↗

arXiv2024

Operational Collective Intelligence of Humans and Machines

We explore the use of aggregative crowdsourced forecasting (ACF) as a mechanism to help operationalize ``collective intelligence'' of human-machine teams for coordinated actions. We adopt the definition for Collective Intelligence as: ``A property of groups that emerges from synergies among data-information-knowledge, software-hardware, and individuals (those with new insights as well as recognized authorities) that enables just-in-time knowledge for better decisions than these three elements acting alone.'' Collective Intelligence emerges from new ways of connecting humans and AI to enable decision-advantage, in part by creating and leveraging additional sources of information that might otherwise not be included. Aggregative crowdsourced forecasting (ACF) is a recent key advancement towards Collective Intelligence wherein predictions (X\% probability that Y will happen) and rationales (why I believe it is this probability that X will happen) are elicited independently from a diverse crowd, aggregated, and then used to inform higher-level decision-making. This research asks whether ACF, as a key way to enable Operational Collective Intelligence, could be brought to bear on operational scenarios (i.e., sequences of events with defined agents, components, and interactions) and decision-making, and considers whether such a capability could provide novel operational capabilities to enable new forms of decision-advantage.

cs.AI↗

arXiv2024

"Define Your Terms" : Enhancing Efficient Offensive Speech Classification with Definition

The propagation of offensive content through social media channels has garnered attention of the research community. Multiple works have proposed various semantically related yet subtle distinct categories of offensive speech. In this work, we explore meta-earning approaches to leverage the diversity of offensive speech corpora to enhance their reliable and efficient detection. We propose a joint embedding architecture that incorporates the input's label and definition for classification via Prototypical Network. Our model achieves at least 75% of the maximal F1-score while using less than 10% of the available training data across 4 datasets. Our experimental findings also provide a case study of training strategies valuable to combat resource scarcity.

cs.CL↗

arXiv2024

The Pulse of Mood Online: Unveiling Emotional Reactions in a Dynamic Social Media Landscape

The rich and dynamic information environment of social media provides researchers, policy makers, and entrepreneurs with opportunities to learn about social phenomena in a timely manner. However, using these data to understand social behavior is difficult due to heterogeneity of topics and events discussed in the highly dynamic online information environment. To address these challenges, we present a method for systematically detecting and measuring emotional reactions to offline events using change point detection on the time series of collective affect, and further explaining these reactions using a transformer-based topic model. We demonstrate the utility of the method by successfully detecting major and smaller events on three different datasets, including (1) a Los Angeles Tweet dataset between Jan. and Aug. 2020, in which we revealed the complex psychological impact of the BlackLivesMatter movement and the COVID-19 pandemic, (2) a dataset related to abortion rights discussions in USA, in which we uncovered the strong emotional reactions to the overturn of Roe v. Wade and state abortion bans, and (3) a dataset about the 2022 French presidential election, in which we discovered the emotional and moral shift from positive before voting to fear and criticism after voting. The capability of our method allows for better sensing and monitoring of population's reactions during crises using online data.

cs.SI↗

arXiv2024

The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations

Large Language Models (LLMs) have seen widespread deployment in various real-world applications. Understanding these biases is crucial to comprehend the potential downstream consequences when using LLMs to make decisions, particularly for historically disadvantaged groups. In this work, we propose a simple method for analyzing and comparing demographic bias in LLMs, through the lens of job recommendations. We demonstrate the effectiveness of our method by measuring intersectional biases within ChatGPT and LLaMA, two cutting-edge LLMs. Our experiments primarily focus on uncovering gender identity and nationality bias; however, our method can be extended to examine biases associated with any intersection of demographic identities. We identify distinct biases in both models toward various demographic identities, such as both models consistently suggesting low-paying jobs for Mexican workers or preferring to recommend secretarial roles to women. Our study highlights the importance of measuring the bias of LLMs in downstream applications to understand the potential for harm and inequitable outcomes.

cs.CL↗

arXiv2023

Ensembled Prediction Intervals for Causal Outcomes Under Hidden Confounding

Causal inference of exact individual treatment outcomes in the presence of hidden confounders is rarely possible. Recent work has extended prediction intervals with finite-sample guarantees to partially identifiable causal outcomes, by means of a sensitivity model for hidden confounding. In deep learning, predictors can exploit their inductive biases for better generalization out of sample. We argue that the structure inherent to a deep ensemble should inform a tighter partial identification of the causal outcomes that they predict. We therefore introduce an approach termed Caus-Modens, for characterizing causal outcome intervals by modulated ensembles. We present a simple approach to partial identification using existing causal sensitivity models and show empirically that Caus-Modens gives tighter outcome intervals, as measured by the necessary interval size to achieve sufficient coverage. The last of our three diverse benchmarks is a novel usage of GPT-4 for observational experiments with unknown but probeable ground truth.

cs.LG↗

arXiv2023

Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning

Temporal knowledge graph (TKG) forecasting benchmarks challenge models to predict future facts using knowledge of past facts. In this paper, we apply large language models (LLMs) to these benchmarks using in-context learning (ICL). We investigate whether and to what extent LLMs can be used for TKG forecasting, especially without any fine-tuning or explicit modules for capturing structural and temporal information. For our experiments, we present a framework that converts relevant historical facts into prompts and generates ranked predictions using token probabilities. Surprisingly, we observe that LLMs, out-of-the-box, perform on par with state-of-the-art TKG models carefully designed and trained for TKG forecasting. Our extensive evaluation presents performances across several models and datasets with different characteristics, compares alternative heuristics for preparing contextual information, and contrasts to prominent TKG methods and simple frequency and recency baselines. We also discover that using numerical indices instead of entity/relation names, i.e., hiding semantic information, does not significantly affect the performance ($\pm$0.4\% Hit@1). This shows that prior semantic knowledge is unnecessary; instead, LLMs can leverage the existing patterns in the context to achieve such performance. Our analysis also reveals that ICL enables LLMs to learn irregular patterns from the historical context, going beyond simple predictions based on common or recent information.

cs.CL↗

arXiv2023

Pandemic Culture Wars: Partisan Differences in the Moral Language of COVID-19 Discussions

Effective response to pandemics requires coordinated adoption of mitigation measures, like masking and quarantines, to curb a virus's spread. However, as the COVID-19 pandemic demonstrated, political divisions can hinder consensus on the appropriate response. To better understand these divisions, our study examines a vast collection of COVID-19-related tweets. We focus on five contentious issues: coronavirus origins, lockdowns, masking, education, and vaccines. We describe a weakly supervised method to identify issue-relevant tweets and employ state-of-the-art computational methods to analyze moral language and infer political ideology. We explore how partisanship and moral language shape conversations about these issues. Our findings reveal ideological differences in issue salience and moral language used by different groups. We find that conservatives use more negatively-valenced moral language than liberals and that political elites use moral rhetoric to a greater extent than non-elites across most issues. Examining the evolution and moralization on divisive issues can provide valuable insights into the dynamics of COVID-19 discussions and assist policymakers in better understanding the emergence of ideological divisions.

cs.SI↗

arXiv2023

"Im not Racist but...": Discovering Bias in the Internal Knowledge of Large Language Models

Large language models (LLMs) have garnered significant attention for their remarkable performance in a continuously expanding set of natural language processing tasks. However, these models have been shown to harbor inherent societal biases, or stereotypes, which can adversely affect their performance in their many downstream applications. In this paper, we introduce a novel, purely prompt-based approach to uncover hidden stereotypes within any arbitrary LLM. Our approach dynamically generates a knowledge representation of internal stereotypes, enabling the identification of biases encoded within the LLM's internal knowledge. By illuminating the biases present in LLMs and offering a systematic methodology for their analysis, our work contributes to advancing transparency and promoting fairness in natural language processing systems.

cs.CL↗