paper-with-me

홈 › Papers

A Cognitively Grounded Bayesian Framework for Misinformation Susceptibility

2026-05-10 · Pranava Madhyastha arxiv

In this (work in progress) paper, we present Bounded Pragmatic Listener (or BPL), a cognitively grounded Bayesian framework for modelling susceptibility to information disorder. BPL extends Rational Speech Act theory with three cognitively motivated bounds derived from the bounded rationality literature with a) a recursion depth bound (that emphasises working memory limits);b) a prior compression parameter (which is oriented at capturing information bottleneck); and c) an availability sample size (that operationalises importance sampling with saliency-weighted proposals). This allows us to test predictions about misinformation susceptibility, annotator disagreement, and the differential vulnerability to mis-, dis-, and mal-information as defined in the Information Disorder framework. We validate BPL on the LIAR and MultiFC benchmarks showcasing competitive veracity classification and experimental support for the depth-mismatch paradox.

📄 PDF Abstract BibTeX arXiv:2605.09483

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility

2026-03-03 · Angana Borah, Zohaib Khan, Rada Mihalcea, Verónica Pérez-Rosas arxiv

Misinformation is a growing societal threat, and susceptibility to misinformative claims varies across demographic groups due to differences in underlying beliefs. As Large Language Models (LLMs) are increasingly used to…

ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles

2026-05-13 · Yitian Yang, Yiqun Duan, Linghan Huang, Yiqi Zhu 외 arxiv

Large language model (LLM)-based multi-agent simulation offers a powerful testbed for studying social opinion dynamics. Yet current approaches often adopt two contrasting methods: either relying on fixed update rules wit…

Persuasion at Play: Understanding Misinformation Dynamics in Demographic-Aware Human-LLM Interactions

2025-03-03 · Angana Borah, Rada Mihalcea, Verónica Pérez-Rosas

Existing challenges in misinformation exposure and susceptibility vary across demographic groups, as some populations are more vulnerable to misinformation than others. Large language models (LLMs) introduce new dimensio…

Misinformation

Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach

2023-11-16 · Yanchen Liu, Mingyu Derek Ma, Wenna Qin, Azure Zhou 외

Susceptibility to misinformation describes the degree of belief in unverifiable claims, a latent aspect of individuals' mental processes that is not observable. Existing susceptibility studies heavily rely on self-report…

Misinformation

Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to Misinformation

2025-07-24 · Kyubeen Han, Junseo Jang, Hongjin Kim, Geunyeong Jeong 외 arxiv

Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs. However, this process may increase the model's depe…