MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs

• URL: http://arxiv.org/abs/2509.16564v1
• Date: Sat, 20 Sep 2025 07:40:48 GMT
• Title: MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMs
• Authors: Jun Rong Brian Chong, Yixuan Tang, Anthony K. H. Tung,
• Abstract summary: Current misinformation detection approaches implicitly assume that misinformation is static.<n>We introduce MPCG, a multi-round, persona-conditioned framework that simulates how claims are iteratively reinterpreted by agents with distinct ideological perspectives.
• Score: 13.91292293823499
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Misinformation evolves as it spreads, shifting in language, framing, and moral emphasis to adapt to new audiences. However, current misinformation detection approaches implicitly assume that misinformation is static. We introduce MPCG, a multi-round, persona-conditioned framework that simulates how claims are iteratively reinterpreted by agents with distinct ideological perspectives. Our approach uses an uncensored large language model (LLM) to generate persona-specific claims across multiple rounds, conditioning each generation on outputs from the previous round, enabling the study of misinformation evolution. We evaluate the generated claims through human and LLM-based annotations, cognitive effort metrics (readability, perplexity), emotion evocation metrics (sentiment analysis, morality), clustering, feasibility, and downstream classification. Results show strong agreement between human and GPT-4o-mini annotations, with higher divergence in fluency judgments. Generated claims require greater cognitive effort than the original claims and consistently reflect persona-aligned emotional and moral framing. Clustering and cosine similarity analyses confirm semantic drift across rounds while preserving topical coherence. Feasibility results show a 77% feasibility rate, confirming suitability for downstream tasks. Classification results reveal that commonly used misinformation detectors experience macro-F1 performance drops of up to 49.7%. The code is available at https://github.com/bcjr1997/MPCG

Related papers

• Context-Adaptive Requirements Defect Prediction through Human-LLM Collaboration [1.4499356176178066]
  We propose a Human-LLM Collaboration (HLC) approach that treats defect prediction as an adaptive process rather than a static classification task.<n>We evaluate this approach using the weak word smell on the QuRE benchmark of 1,266 annotated Mercedes-Benz requirements.
  arXiv  Detail & Related papers  (2026-01-05T10:00:14Z)
• QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation [14.312693191309101]
  Dynamic Retrieval-Augmented Generation adaptively determines when to retrieve during generation to hallucinations in large language models.<n>We propose QuCo-RAG, which shifts from subjective confidence to objective statistics computed from pre-training data.<n>Our method quantifies uncertainty through two stages: (1) before generation, we identify low-frequency entities indicating long-tail knowledge gaps; (2) during generation, we verify entity co-occurrence in the pre-training corpus, where zero co-occurrence often signals hallucination risk.
  arXiv  Detail & Related papers  (2025-12-22T08:28:05Z)
• Simulating Misinformation Propagation in Social Networks using Large Language Models [4.285464959472458]
  Misinformation on social media thrives on surprise, emotion, and identity-driven reasoning, often amplified through human cognitive biases.<n>To investigate these mechanisms, we model large language model (LLM) personas as synthetic agents that mimic user-level biases, ideological alignments, and trust misinformations.<n>Within this setup, we introduce an auditor-conditioned-node framework to simulate and analyze how misinformation evolves as it circulates through networks of such agents.
  arXiv  Detail & Related papers  (2025-11-13T15:01:19Z)
• Taming a Retrieval Framework to Read Images in Humanlike Manner for Augmenting Generation of MLLMs [23.638717678491986]
  Multimodal large language models (MLLMs) often fail in fine-grained visual question answering.<n>We present Human-Like Retrieval-Augmented Generation (HuLiRAG), a framework that stages multimodal reasoning as a what--where--reweight'' cascade.
  arXiv  Detail & Related papers  (2025-10-12T03:22:33Z)
• Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images [96.43608872116347]
  AnomReason is a large-scale benchmark with structured annotations as quadruple textbfAnomAgent<n>AnomReason and AnomAgent serve as a foundation for measuring and improving the semantic plausibility of AI-generated images.
  arXiv  Detail & Related papers  (2025-10-11T14:09:24Z)
• Fairness Testing in Retrieval-Augmented Generation: How Small Perturbations Reveal Bias in Small Language Models [0.1876920697241348]
  This study conducts fairness testing through metamorphic testing (MT), introducing controlled demographic perturbations in prompts to assess fairness in sentiment analysis performed by three Small Language Models (SLMs)<n>Results show that minor demographic variations can break up to one third of metamorphic relations (MRs)<n>A detailed analysis of these failures reveals a consistent bias hierarchy, with perturbations involving racial cues being the predominant cause of the violations.
  arXiv  Detail & Related papers  (2025-09-30T17:42:35Z)
• Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models [57.834711966432685]
  Bullshit, as conceptualized by philosopher Harry Frankfurt, refers to statements made without regard to their truth value.<n>We introduce the Bullshit Index, a novel metric quantifying large language model's indifference to truth.<n>We observe prevalent machine bullshit in political contexts, with weasel words as the dominant strategy.
  arXiv  Detail & Related papers  (2025-07-10T07:11:57Z)
• Can Reasoning Help Large Language Models Capture Human Annotator Disagreement? [84.32752330104775]
  Variation in human annotation (i.e., disagreements) is common in NLP.<n>We evaluate the influence of different reasoning settings on Large Language Model disagreement modeling.<n>Surprisingly, our results show that RLVR-style reasoning degrades performance in disagreement modeling.
  arXiv  Detail & Related papers  (2025-06-24T09:49:26Z)
• Estimating Commonsense Plausibility through Semantic Shifts [66.06254418551737]
  We propose ComPaSS, a novel discriminative framework that quantifies commonsense plausibility by measuring semantic shifts.<n> Evaluations on two types of fine-grained commonsense plausibility estimation tasks show that ComPaSS consistently outperforms baselines.
  arXiv  Detail & Related papers  (2025-02-19T06:31:06Z)
• Contrastive Learning with Counterfactual Explanations for Radiology Report Generation [83.30609465252441]
  We propose a textbfCountertextbfFactual textbfExplanations-based framework (CoFE) for radiology report generation. Counterfactual explanations serve as a potent tool for understanding how decisions made by algorithms can be changed by asking what if'' scenarios. Experiments on two benchmarks demonstrate that leveraging the counterfactual explanations enables CoFE to generate semantically coherent and factually complete reports.
  arXiv  Detail & Related papers  (2024-07-19T17:24:25Z)
• Cobra Effect in Reference-Free Image Captioning Metrics [58.438648377314436]
  A proliferation of reference-free methods, leveraging visual-language pre-trained models (VLMs), has emerged. In this paper, we study if there are any deficiencies in reference-free metrics. We employ GPT-4V as an evaluative tool to assess generated sentences and the result reveals that our approach achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2024-02-18T12:36:23Z)
• Using Natural Language Explanations to Rescale Human Judgments [81.66697572357477]
  We propose a method to rescale ordinal annotations and explanations using large language models (LLMs)<n>We feed annotators' Likert ratings and corresponding explanations into an LLM and prompt it to produce a numeric score anchored in a scoring rubric.<n>Our method rescales the raw judgments without impacting agreement and brings the scores closer to human judgments grounded in the same scoring rubric.
  arXiv  Detail & Related papers  (2023-05-24T06:19:14Z)
• Elastic Weight Removal for Faithful and Abstractive Dialogue Generation [61.40951756070646]
  A dialogue system should generate responses that are faithful to the knowledge contained in relevant documents. Many models generate hallucinated responses instead that contradict it or contain unverifiable information. We show that our method can be extended to simultaneously discourage hallucinations and extractive responses.
  arXiv  Detail & Related papers  (2023-03-30T17:40:30Z)
• Making a (Counterfactual) Difference One Rationale at a Time [5.97507595130844]
  We investigate whether counterfactual data augmentation, without human assistance, can improve the performance of the selector. Our results show that CDA produces rationales that better capture the signal of interest.
  arXiv  Detail & Related papers  (2022-01-13T19:05:02Z)
• Variational Mutual Information Maximization Framework for VAE Latent Codes with Continuous and Discrete Priors [5.317548969642376]
  Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. We propose Variational Mutual Information Maximization Framework for VAE to address this issue.
  arXiv  Detail & Related papers  (2020-06-02T09:05:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.