Skip to content

Explore papers

Filter by research area, year and venue. Every filter is in the address bar, so you can share a view as a link.

Spread & networksPlatforms, policy & society Engagement, User Satisfaction, and the Amplification of Divisive Content on Social MediaTwitter's engagement-based ranking algorithm amplifies emotionally charged and partisan divisive content beyond what users report wanting to see. Through a pre-registered experiment comparing the engagement-based timeline to a reverse-chronological baseline, the authors show the algorithm increases anger, sadness, and out-group… Mills et al. · arXiv · 2023

LLMs & generative AIDeepfakes & multimodal FLIRT: Feedback Loop In-context Red TeamingFLIRT automates red teaming of generative models by using in-context learning to generate adversarial prompts in a feedback loop: a red language model generates candidate prompts, they are evaluated against a target model (e.g., text-to-image or text-to-text), safety classifiers assess the outputs, and results feed back to refine future… Mehrabi et al. · arXiv · 2023

Platforms, policy & societyLLMs & generative AI Disinformation 2.0 in the Age of AI: A Cybersecurity PerspectiveDisinformation should be treated as a cybersecurity threat, particularly as AI advances enable its creation and dissemination at unprecedented scale. The paper introduces "disinformation 2.0"—where generative AI, perturbation techniques, detection evasion, and optimized spread strategies make false content more persuasive and harder to… Mazurczyk et al. · ACM Publication · 2023

LLMs & generative AIPlatforms, policy & society Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models' AlignmentThis survey provides a comprehensive framework for evaluating LLM trustworthiness across seven dimensions: reliability, safety, fairness, resistance to misuse, explainability, social norms, and robustness. The authors present a detailed taxonomy with 29 sub-categories, conduct empirical measurements on widely-used LLMs (GPT-4, ChatGPT,… Liu et al. · arXiv · 2023

LLMs & generative AIPlatforms, policy & society Generative Language Models and Automated Influence Operations: Emerging Threats and Potential MitigationsGenerative language models like GPT-3 and ChatGPT could significantly expand the scale and scope of influence operations by automating high-quality propaganda generation, lowering barriers to entry for new propagandists, and enabling novel tactics. The authors use an Actor-Behavior-Content (ABC) framework to identify how these models… Goldstein et al. · arXiv · 2023

LLMs & generative AIPlatforms, policy & society Toxicity in ChatGPT: Analyzing Persona-assigned Language ModelsLarge-scale empirical analysis of ChatGPT's toxicity across 90 personas using 500K+ generations. Assigning personas via the system parameter increases toxicity up to 6×, with variation depending on persona characteristics and target entities. Deshpande et al. · arXiv · 2023

LLMs & generative AIDetection methods A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and ExplainabilityA comprehensive survey of trustworthy Graph Neural Networks covering four critical dimensions: privacy attacks and defenses against membership/property inference and model extraction; robustness against adversarial perturbations; fairness mechanisms to prevent discrimination in graph-based predictions; and explainability methods to… Dai et al. · ACM Computing Surveys · 2023

LLMs & generative AIDatasets & evaluation A Survey on Evaluation of Large Language ModelsThis survey provides a comprehensive review of evaluation methodologies for large language models across three dimensions: what to evaluate, where to evaluate, and how to evaluate. The paper encompasses evaluation tasks spanning natural language processing, natural language generation, robustness, ethics, bias detection, trustworthiness,… Chang et al. · Journal of the ACM · 2023

LLMs & generative AIDeepfakes & multimodal A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTThis is the first comprehensive survey of AI-Generated Content (AIGC) covering the history, techniques, and applications of generative models from GANs through ChatGPT. It addresses both the impressive capabilities of these models (text, image, audio, video generation) and critical concerns including factuality, security, privacy, and… Cao et al. · J. ACM, Vol. 37, No. 4 · 2023

LLMs & generative AIDetection methods Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionThis paper introduces SELF-RAG (Self-Reflective Retrieval-Augmented Generation), a framework that teaches language models to adaptively decide when to retrieve external passages, generate factually grounded responses, and critique their own outputs. Using special "reflection tokens," the model learns to self-evaluate at inference time… Asai et al. · arXiv · 2023

LLMs & generative AIDetection methods Disinformation Capabilities of Large Language ModelsComprehensive empirical evaluation of 10 LLMs' ability to generate disinformation news articles. Most models readily generate convincing disinformation that agrees with dangerous narratives; Falcon is the sole exception. Vykopal et al. · arXiv · 2023

LLMs & generative AIDetection methods Can AI-Generated Text be Reliably Detected?This paper stress-tests AI-text detectors using a novel recursive paraphrasing attack, showing that watermarking-based, neural network-based, and retrieval-based detectors can be reliably broken with only minor text degradation. The work establishes a theoretical connection between detector AUROC and the total variation distance between… Sadasivan et al. · arXiv · 2023

LLMs & generative AIDetection methods On the Risk of Misinformation Pollution with Large Language ModelsThis paper investigates how modern LLMs can be misused to generate convincing misinformation at scale and its impact on downstream NLP applications. Using GPT-3.5 as a misinformation generator, the authors demonstrate that synthetically-generated false information can significantly degrade ODQA system performance (up to 87% in some… Pan et al. · arXiv · 2023

LLMs & generative AIDetection methods A Watermark for Large Language ModelsProposes a watermarking scheme for large language models that embeds imperceptible signals into generated text, enabling detection of machine-generated content without access to model parameters or APIs. The watermark works by promoting a randomized set of "green" tokens during decoding and can be detected using a statistical z-test; the… Kirchenbauer et al. · arXiv · 2023

LLMs & generative AIDetection methods Combating Misinformation in the Age of LLMs: Opportunities and ChallengesThis survey systematically reviews how large language models (LLMs) can both combat misinformation and generate it at scale. LLMs offer opportunities for detection, intervention, and attribution through their world knowledge and reasoning abilities, but also pose challenges as they can create deceptive content intentionally or through… Chen & Shu · arXiv · 2023

Spread & networksDetection methods "This is Fake! Shared it by Mistake": Assessing the Intent of Fake News SpreadersThis work is the first to systematically assess whether individuals spread fake news intentionally or unintentionally. The authors propose an influence graph that captures psychological (internal) and social (external) factors driving unintentional spreading, validate it on two datasets with manually-annotated spreader intent, and… Zhou et al. · ACM Web Conference 2022 · 2022

LLMs & generative AIDetection methods All the News That's Fit to Fabricate: AI-Generated Text as a Tool of Media MisinformationThree experiments investigate whether AI-generated news text can be credible and influence public opinion. The authors find that GPT-2 models (355M to 1.5B parameters) generate text nearly indistinguishable from human-written baseline news, particularly when politically congruent stories are paired with partisan audiences. Kreps et al. · Journal of Experimental Political Science · 2022

LLMs & generative AIBots & coordinated campaigns Red Teaming Language Models with Language ModelsThis paper demonstrates that language models can automatically discover a wide range of harmful behaviors in other language models through "red teaming"—using one LM to generate adversarial test cases that probe another LM's vulnerabilities. The authors explore multiple generation strategies (zero-shot, few-shot, supervised learning,… Perez et al. · arXiv · 2022

LLMs & generative AIDatasets & evaluation Discovering Language Model Behaviors with Model-Written EvaluationsRather than manually creating evaluation datasets, this work proposes using language models themselves to generate high-quality evaluations for testing diverse LM behaviors. The authors generate 154 datasets testing behaviors spanning personality, political views, ethics, and goal-seeking. Perez et al. · 2022

LLMs & generative AIDetection methods Causal Machine Learning: A Survey and Open ProblemsComprehensive survey of causal machine learning (CausalML), which formalizes data generation as a structural causal model to reason about interventions and counterfactuals. Categorizes 191 pages of CausalML work into five groups—causal supervised learning, causal generative modeling, causal explanations, causal fairness, and causal… Kaddour et al. · arXiv · 2022

Platforms, policy & societyDetection methods A Comprehensive Survey on Trustworthy Recommender SystemsRecommender systems, while beneficial to users, can amplify harmful content, introduce discrimination, and enable adversarial attacks. This survey provides a comprehensive framework for trustworthy recommender systems across six critical dimensions: Safety & Robustness (defense against adversarial attacks), Non-discrimination & Fairness… Fan et al. · ACM Computing Surveys · 2022

Spread & networksPlatforms, policy & society Right-Wing YouTube: A Supply and Demand PerspectiveYouTube has become the dominant platform for right-wing political content in the US, driven by supply-side affordances (low creation barriers, monetization, algorithmic recommendation) and demand-side audience appetite for alternative media. Using longitudinal analysis of creator clusters (Conservative, Alt-Lite, Alt-Right), the authors… Munger & Phillips · The International Journal of Press/Politics · 2022

Psychology & interventionsFact-checking & verification The psychological drivers of misinformation belief and its resistance to correctionThis comprehensive review establishes that misinformation's power lies not in exposure but in how cognitive, social, and affective factors shape belief formation and persist even after correction. False beliefs arise from intuitive thinking, memory failures, emotional content, in-group bias, and source credibility judgments; corrections… Ecker et al. · Nature Reviews Psychology · 2022

Psychology & interventionsPlatforms, policy & society Measuring the impact of COVID-19 vaccine misinformation on vaccination intent in the UK and USARandomized controlled trial on 8,001 respondents (4,000 UK, 4,001 USA) measuring causal impact of exposure to COVID-19 vaccine misinformation. Exposure to misinformation reduced vaccination intent by 6.2 percentage points in the UK and 6.4 in the USA relative to exposure to factual information. Loomba et al. · Nature Human Behaviour · 2021