Gourab Ghoshal

Neeley Pate, Adiba Mahbub Proma, Hangfeng He et al.

Motivated reasoning -- the idea that individuals processing information may be motivated to reach a certain conclusion, whether it be accurate or predetermined -- has been well-explored as a human phenomenon. However, it is unclear whether base LLMs mimic these motivational changes. 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 smaller standard deviations and inaccurate argument strength assessments. We emphasize the importance of these findings for researchers using LLMs to automate tasks such as survey data collection and argument assessment.

Adiba Mahbub Proma, Neeley Pate, James N. Druckman et al.

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.

Raiyan Abdul Baten, Ali Sarosh Bangash, Krish Veera et al.

Can peer recommendation engines elevate people's creative performances in self-organizing social networks? Answering this question requires resolving challenges in data collection (e.g., tracing inspiration links and psycho-social attributes of nodes) and intervention design (e.g., balancing idea stimulation and redundancy in evolving information environments). We trained a model that predicts people's ideation performances using semantic and network-structural features in an online platform. Using this model, we built SocialMuse, which maximizes people's predicted performances to generate peer recommendations for them. We found treatment networks leveraging SocialMuse outperforming AI-agnostic control networks in several creativity measures. The treatment networks were more decentralized than the control, as SocialMuse increasingly emphasized network-structural features at large network sizes. This decentralization spreads people's inspiration sources, helping inspired ideas stand out better. Our study provides actionable insights into building intelligent systems for elevating creativity.

Adiba Mahbub Proma, Neeley Pate, James Druckman et al.

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.

Rasoul Shafipour, Raiyan Abdul Baten, Md Kamrul Hasan et al.

In this study, we explore peer-interaction effects in online networks on speaking skill development. In particular, we present an evidence for gradual buildup of skills in a small-group setting that has not been reported in the literature. We introduce a novel dataset of six online communities consisting of 158 participants focusing on improving their speaking skills. They video-record speeches for 5 prompts in 10 days and exchange comments and performance-ratings with their peers. We ask (i) whether the participants' ratings are affected by their interaction patterns with peers, and (ii) whether there is any gradual buildup of speaking skills in the communities towards homogeneity. To analyze the data, we employ tools from the emerging field of Graph Signal Processing (GSP). GSP enjoys a distinction from Social Network Analysis in that the latter is concerned primarily with the connection structures of graphs, while the former studies signals on top of graphs. We study the performance ratings of the participants as graph signals atop underlying interaction topologies. Total variation analysis of the graph signals show that the participants' rating differences decrease with time (slope=-0.04, p<0.01), while average ratings increase (slope=0.07, p<0.05)--thereby gradually building up the ratings towards community-wide homogeneity. We provide evidence for peer-influence through a prediction formulation. Our consensus-based prediction model outperforms baseline network-agnostic regression models by about 23% in predicting performance ratings. This, in turn, shows that participants' ratings are affected by their peers' ratings and the associated interaction patterns, corroborating previous findings. Then, we formulate a consensus-based diffusion model that captures these observations of peer-influence from our analyses.

Ru Zhao, Vivian Li, Hugo Barbosa et al.

This paper presents a description and evaluation of the ROC Speak system, a platform that allows ubiquitous access to communication skills training. ROC Speak (available at rocspeak.com) enables anyone to go to a website, record a video, and receive feedback on smile intensity, body movement, volume modulation, filler word usage, unique word usage, word cloud of the spoken words, in addition to overall assessment and subjective comments by peers. Peer comments are automatically ranked and sorted for usefulness and sentiment (i.e., positive vs. negative). We evaluated the system with a diverse group of 56 online participants for a 10-day period. Participants submitted responses to career oriented prompts every other day. The participants were randomly split into two groups: 1) treatment - full feedback from the ROC Speak system; 2) control - written feedback from online peers. When judged by peers (p<.001) and independent raters (p<.05), participants from the treatment group demonstrated statistically significant improvement in overall speaking skills rating while the control group did not. Furthermore, in terms of speaking attributes, treatment group showed an improvement in friendliness (p<.001), vocal variety (p<.05) and articulation (p<.01).