arXiv subjects

Adiba Mahbub Proma

Publications and source records attributed to Adiba Mahbub Proma.

9 recordsLinked to original sources

arXiv2026

Can LLMs Emulate Human Belief Dynamics?

Can LLMs simulate how humans form and change beliefs in social networks? We put this to the test by replicating an established study on belief dynamics, evaluating 12 LLMs across multiple model families and parameter sizes. The answer is a clear no, and in systematic ways. LLMs fail to capture initial human belief distributions and tend to be overall more conformist than humans, shifting their responses to align with those around them. They also take a nuanced approach to emulating human homophilic tendencies within networks. Our findings carry a double payoff: they highlight fundamental properties of LLM behavior, and they raise a sharp warning against deploying LLMs as human proxies in social simulations.

cs.SI↗

arXiv2026

Replicating Human Motivated Reasoning Studies with LLMs

Motivated reasoning - the idea that individuals processing information may be motivated to either arrive at accurate beliefs or arrive at desired conclusions - has been well-explored as a human phenomenon. However, it remains unclear whether base LLMs are affected by motivational manipulations. Replicating 4 prior political motivated reasoning studies, we find that base LLM behavior does not align with expected human behavior. Furthermore, base LLM behavior across models shares some similarities, such as when selecting to abstain from question answering and incorporating provided arguments into opinions. The results suggest that base LLMs may not emulate human motivated reasoning processes. We emphasize the importance of these findings for researchers using LLMs to for certain tasks such as opinion replication and argument assessment.

cs.HC↗

arXiv2025

MERIT: Modular Framework for Multimodal Misinformation Detection with Web-Grounded Reasoning

We present MERIT, an inference-time modular framework for multimodal misinformation detection that decomposes verification into four specialized modules: visual forensics, cross-modal alignment, retrieval-augmented claim verification, and calibrated judgment. On MMFakeBench, MERIT with GPT-4o-mini achieves 81.65% F1, outperforming all reported zero-shot baselines including GPT-4V with MMD-Agent (74.0% F1). A controlled same-model evaluation confirms gains stem from architectural design: MERIT achieves 6.14 points higher misinformation recall than MMD-Agent under identical model conditions, with per-class gains of +18.0 on visual distortion and +5.33 on textual distortion. Ablation studies reveal non-overlapping module specialization, where removing any module disproportionately degrades its target category while leaving others intact. Test set evaluation on 5,000 samples confirms generalization within 0.21 F1 points of validation results. The framework operates with any instruction-following vision-language model and produces citation-linked rationales for human review.

cs.AI↗

arXiv2025

Personalized Large Language Models Can Increase the Belief Accuracy of Social Networks

Large language models (LLMs) are increasingly involved in shaping public understanding on contested issues. This has led to substantial discussion about the potential of LLMs to reinforce or correct misperceptions. While existing literature documents the impact of LLMs on individuals' beliefs, limited work explores how LLMs affect social networks. We address this gap with a pre-registered experiment (N = 1265) around the 2024 US presidential election, where we empirically explore the impact of personalized LLMs on belief accuracy in the context of social networks. The LLMs are constructed to be personalized, offering messages tailored to individuals' profiles, and to have guardrails for accurate information retrieval. We find that the presence of a personalized LLM leads individuals to update their beliefs towards the truth. More importantly, individuals with a personalized LLM in their social network not only choose to follow it, indicating they would like to obtain information from it in subsequent interactions, but also construct subsequent social networks to include other individuals with beliefs similar to the LLM -- in this case, more accurate beliefs. Therefore, our results show that LLMs have the capacity to influence individual beliefs and the social networks in which people exist, and highlight the potential of LLMs to act as corrective agents in online environments. Our findings can inform future strategies for responsible AI-mediated communication.

cs.SI↗

arXiv2025

Evidence-Grounded Multimodal Misinformation Detection with Attention-Based GNNs

Multimodal out-of-context (OOC) misinformation is misinformation that repurposes real images with unrelated or misleading captions. Detecting such misinformation is challenging because it requires resolving the context of the claim before checking for misinformation. Many current methods, including LLMs and LVLMs, do not perform this contextualization step. LLMs hallucinate in absence of context or parametric knowledge. In this work, we propose a graph-based method that evaluates the consistency between the image and the caption by constructing two graph representations: an evidence graph, derived from online textual evidence, and a claim graph, from the claim in the caption. Using graph neural networks (GNNs) to encode and compare these representations, our framework then evaluates the truthfulness of image-caption pairs. We create datasets for our graph-based method, evaluate and compare our baseline model against popular LLMs on the misinformation detection task. Our method scores $93.05\%$ detection accuracy on the evaluation set and outperforms the second-best performing method (an LLM) by $2.82\%$, making a case for smaller and task-specific methods.

cs.LG↗

arXiv2025

How LLMs Fail to Support Fact-Checking

While Large Language Models (LLMs) can amplify online misinformation, they also show promise in tackling misinformation. In this paper, we empirically study the capabilities of three LLMs -- ChatGPT, Gemini, and Claude -- in countering political misinformation. We implement a two-step, chain-of-thought prompting approach, where models first identify credible sources for a given claim and then generate persuasive responses. Our findings suggest that models struggle to ground their responses in real news sources, and tend to prefer citing left-leaning sources. We also observe varying degrees of response diversity among models. Our findings highlight concerns about using LLMs for fact-checking through only prompt-engineering, emphasizing the need for more robust guardrails. Our results have implications for both researchers and non-technical users.

cs.CL↗

arXiv2024

Exploring the Role of Randomization on Belief Rigidity in Online Social Networks

People often stick to their existing beliefs, ignoring contradicting evidence or only interacting with those who reinforce their views. Social media platforms often facilitate such tendencies of homophily and echo-chambers as they promote highly personalized content to maximize user engagement. However, increased belief rigidity can negatively affect real-world policy decisions such as leading to climate change inaction and increased vaccine hesitancy. To understand and effectively tackle belief rigidity on online social networks, designing and evaluating various intervention strategies is crucial, and increasing randomization in the network can be considered one such intervention. In this paper, we empirically quantify the effects of a randomized social network structure on belief rigidity, specifically examining the potential benefits of introducing randomness into the network. We show that individuals' beliefs are positively influenced by peer opinions, regardless of whether those opinions are similar to or differ from their own by passively sensing belief rigidity through our experimental framework. Moreover, people incorporate a slightly higher variety of different peers (based on their opinions) into their networks when the recommendation algorithm provides them with diverse content, compared to when it provides them with similar content. Our results indicate that in some cases, there might be benefits to randomization, providing empirical evidence that a more randomized network could be a feasible way of helping people get out of their echo-chambers. Our findings have broader implications in computing and platform design of social media, and can help combat overly rigid beliefs in online social networks.

cs.SI↗

arXiv2023

Don't follow the leader: Independent thinkers create scientific innovation

Academic success is distributed unequally; a few top scientists receive the bulk of attention, citations, and resources. However, do these ``superstars" foster leadership in scientific innovation? We introduce three information-theoretic measures that quantify novelty, innovation, and impact from scholarly citation networks, and compare the scholarly output of scientists who are either not connected or strongly connected to superstar scientists. We find that while connected scientists do indeed publish more, garner more citations, and produce more diverse content, this comes at a cost of lower innovation and higher redundancy of ideas. Further, once one removes papers co-authored with superstars, the academic output of these connected scientists diminishes. In contrast, authors that produce innovative content without the benefit of collaborations with scientific superstars produce papers that connect a greater diversity of concepts, publish more, and have comparable citation rates, once one controls for transferred prestige of superstars. On balance, our results indicate that academia pays a price by focusing attention and resources on superstars.

cs.DL↗

arXiv2022

NADBenchmarks -- a compilation of Benchmark Datasets for Machine Learning Tasks related to Natural Disasters

Climate change has increased the intensity, frequency, and duration of extreme weather events and natural disasters across the world. While the increased data on natural disasters improves the scope of machine learning (ML) in this field, progress is relatively slow. One bottleneck is the lack of benchmark datasets that would allow ML researchers to quantify their progress against a standard metric. The objective of this short paper is to explore the state of benchmark datasets for ML tasks related to natural disasters, categorizing them according to the disaster management cycle. We compile a list of existing benchmark datasets introduced in the past five years. We propose a web platform - NADBenchmarks - where researchers can search for benchmark datasets for natural disasters, and we develop a preliminary version of such a platform using our compiled list. This paper is intended to aid researchers in finding benchmark datasets to train their ML models on, and provide general directions for topics where they can contribute new benchmark datasets.

cs.LG↗