arXiv subjects

Raiyan Abdul Baten

Publications and source records attributed to Raiyan Abdul Baten.

At least 19 recordsLinked to original sources

arXiv2026

Anchorless Diversification for Parallel LLM Ideation

LLMs are increasingly used to generate candidate-idea pools for creative tasks where broad exploration is valuable. Parallel inference can be attractive in this setting when it broadens the pool while retaining quality and cost efficiency. We study inference-time controls for candidate-pool diversification, asking whether anchorless methods can rival methods that depend on observed seed ideas. Across three creative task families, we compare independent generation and semantic direction stratification with self-, peer-, and representative-anchor baselines, under neutral and population-referential divergent instructions. Population-referential divergence is a strong low-cost baseline, increasing semantic diversity while preserving quality proxies. Semantic direction stratification is stronger: a single planning call organizes generations across broad semantic directions, yielding the best diversity--quality--compute frontier. Anchored regeneration can be strong in final-pool diversity, but its advantage shrinks under full-pipeline token accounting. These results establish practical anchorless baselines for open-ended LLM ideation.

cs.AI↗

arXiv2026

Ex Ante Evaluation of AI-Induced Idea Diversity Collapse

Creative AI systems are typically evaluated at the level of individual utility, yet creative outputs are consumed in populations: an idea loses value when many others produce similar ones. This creates an evaluation blind spot, as AI can improve individual outputs while increasing population-level crowding. We introduce a human-relative framework for benchmarking AI-induced human diversity collapse without requiring human-AI interaction data, providing an ex ante protocol to estimate crowding risk from model-only generations and matched unaided human baselines. By modeling ideas as congestible resources, we show that source-level crowding is identifiable from within-distribution comparisons, yielding an excess-crowding coefficient $Δ$ and a human-relative diversity ratio $ρ$. We show that $ρ\ge1$ is the no-excess-crowding parity condition and connect $Δ$ to an adoption game with exposure-dependent redundancy costs. Across short stories, marketing slogans, and alternative-uses tasks, three frontier LLMs fall below parity across crowding kernels. Estimates stabilize with feasible model-only sample sizes. Importantly, generation-protocol variants show that crowding can be reduced through targeted design, making diversity collapse an actionable, development-time evaluation target for population-aware creative AI.

cs.AI↗

arXiv2026

Beginner's Charm: Beginner-Heavy Teams Are Associated With High Scientific Disruption

Teams now drive most scientific advances, yet the impact of absolute beginners -- authors with no prior publications -- remains understudied. Analyzing over 29 million articles published between 1941 and 2020 across disciplines and team sizes, we uncover a near-universal and previously undocumented pattern: teams with a higher fraction of beginners are systematically more disruptive and innovative. Their contributions are linked to distinct knowledge-integration behaviors, including drawing on broader and less canonical prior work and producing more atypical recombinations. Collaboration structure further shapes outcomes: disruption is high when beginners work with early-career colleagues or with co-authors who have disruptive track records. Although disruption and citations are negatively correlated overall, highly disruptive papers from beginner-heavy teams are highly cited. These findings reveal a ``beginner's charm'' in science, highlighting the underrecognized yet powerful value of beginner fractions in teams and suggesting actionable strategies for fostering a thriving ecosystem of innovation in science and technology.

cs.DL↗

arXiv2026

General Intellectual Humility Is Malleable Through AI-Mediated Reflective Dialogue

General intellectual humility (GIH) -- the recognition that one's beliefs may be fallible and revisable -- is associated with improved reasoning, learning, and social discourse, yet is widely regarded as a stable trait resistant to intervention. We test whether GIH can be elevated through a conversational intervention that combines staged cognitive scaffolding with personalized Socratic reflection. In a randomized controlled experiment (N=400), participants engaged in a structured, LLM-mediated dialogue that progressed from conceptual understanding of intellectual humility to applying, analyzing, evaluating, and generating novel, self-relevant scenarios that instantiate it. Relative to a time-matched control, the intervention produced a systematic increase in GIH, reduced rank-order stability, and tripled the rate of reliable individual improvement. Crucially, these effects persisted over a two-week follow-up without detectable decay. The effects generalized across political affiliation and did not depend on baseline personality profile. These findings challenge the prevailing pessimism regarding the malleability of GIH and suggest that scaffolded, Socratic reflection delivered through structured dialogue can produce durable changes in general intellectual humility.

cs.HC↗

arXiv2026

Strategic Adaptation Under Contextual Change: Insights from a Dyadic Negotiation Testbed for AI Coaching Technologies

Strategic adaptation -- the ability to adjust interaction behavior in response to changing constraints and leverage -- is a central goal of negotiation training and an emerging target for AI coaching systems. However, adaptation is difficult to evaluate because adaptation-relevant moments arise unpredictably in typical tasks. We study a reusable dyadic negotiation testbed that employs a controlled midstream change in one party's outside alternative as a repeatable perturbation to stress-test adaptation. In a six-round chat-based negotiation study (N=100), the perturbation reliably reorganized interaction dynamics: transitions between integrative (cooperative) and distributive (positional) behaviors declined, behavioral diversity narrowed, and interactions drifted toward more distributive tactics. Critically, this distributive drift predicted worse relational experience net of objective outcomes, and adaptation patterns were path dependent on prior behavior. These results establish a methodological bridge for evaluating and comparing AI coaching systems on strategic adaptation as a process and identify failure modes and design targets for adaptive interaction support.

cs.HC↗

arXiv2026

From semantic memory to collective creativity: A generative cognitive foundation for social creativity models

Simulation-based theory development has yielded powerful insights into collective performance by linking social structure to emergent outcomes, yet it has struggled to extend to collective creativity. Creativity is hard to capture purely at the social level, as novel ideas are generated through cognitive mechanisms. To address this gap, we introduce a multi-level socio-cognitive agent-based framework in which agents share a common semantic vocabulary and substrate but differ in semantic network topology. A single generative parameter tunes semantic modularity, yielding emergent individual differences in ideational breadth. When agents exchange ideation traces, two canonical social-creativity phenomena arise without being imposed: lower pre-interaction ideation overlap predicts larger stimulation gains, and shared inspiration sources induce network-level redundancy. The framework enables mechanistic theory-building about cognition and social structure in collective creativity.

cs.SI↗

arXiv2025

MuseScorer: Idea Originality Scoring At Scale

An objective, face-valid method for scoring idea originality is to measure each idea's statistical infrequency within a population -- an approach long used in creativity research. Yet, computing these frequencies requires manually bucketing idea rephrasings, a process that is subjective, labor-intensive, error-prone, and brittle at scale. We introduce MuseScorer, a fully automated, psychometrically validated system for frequency-based originality scoring. MuseScorer integrates a Large Language Model (LLM) with externally orchestrated retrieval: given a new idea, it retrieves semantically similar prior idea-buckets and zero-shot prompts the LLM to judge whether the idea fits an existing bucket or forms a new one. These buckets enable frequency-based originality scoring without human annotation. Across five datasets N_{participants}=1143, n_{ideas}=16,294), MuseScorer matches human annotators in idea clustering structure (AMI = 0.59) and participant-level scoring (r = 0.89), while demonstrating strong convergent and external validity. The system enables scalable, intent-sensitive, and human-aligned originality assessment for creativity research.

cs.CL↗

arXiv2025

The Wisdom of Intellectually Humble Networks

People's collectively shared beliefs can have significant social implications, including on democratic processes and policies. Unfortunately, as people interact with peers to form and update their beliefs, various cognitive and social biases can hinder their collective wisdom. In this paper, we probe whether and how the psychological construct of intellectual humility can modulate collective wisdom in a networked interaction setting. Through agent-based modeling and data-calibrated simulations, we provide a proof of concept demonstrating that intellectual humility can foster more accurate estimations while mitigating polarization in social networks. We investigate the mechanisms behind the performance improvements and confirm robustness across task settings and network structures. Our work can guide intervention designs to capitalize on the promises of intellectual humility in boosting collective wisdom in social networks.

cs.SI↗

arXiv2024

AI Can Enhance Creativity in Social Networks

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.

cs.AI↗

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↗

arXiv2024

Context-Aware Prediction of User Engagement on Online Social Platforms

The success of online social platforms hinges on their ability to predict and understand user behavior at scale. Here, we present data suggesting that context-aware modeling approaches may offer a holistic yet lightweight and potentially privacy-preserving representation of user engagement on online social platforms. Leveraging deep LSTM neural networks to analyze more than 100 million Snapchat sessions from almost 80.000 users, we demonstrate that patterns of active and passive use are predictable from past behavior (R2=0.345) and that the integration of context features substantially improves predictive performance compared to the behavioral baseline model (R2=0.522). Features related to smartphone connectivity status, location, temporal context, and weather were found to capture non-redundant variance in user engagement relative to features derived from histories of in-app behaviors. Further, we show that a large proportion of variance can be accounted for with minimal behavioral histories if momentary context is considered (R2=0.442). These results indicate the potential of context-aware approaches for making models more efficient and privacy-preserving by reducing the need for long data histories. Finally, we employ model explainability techniques to glean preliminary insights into the underlying behavioral mechanisms. Our findings are consistent with the notion of context-contingent, habit-driven patterns of active and passive use, underscoring the value of contextualized representations of user behavior for predicting user engagement on social platforms.

cs.LG↗

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↗

arXiv2021

Creativity in social networks is enhanced by 'Goldilocks' dispersal of ideators' visibility

Recent works suggest that striking a balance between maximizing idea stimulation and minimizing idea redundancy can elevate creativity in self-organizing social networks. We explore whether dispersing the visibility of idea generators can help achieve such a trade-off. We employ popularity signals (follower counts) of participants as an external source of variation in network structures, which we control across four randomized study conditions. We observe that popularity signals influence inspiration-seeking ties, partly by biasing people's perception of their peers' creativity. Networks that partially disperse the ideators' visibility using this external signal show reduced idea-redundancy and elevated creativity. However, extreme dispersal leads to inferior creativity by narrowing the range of idea stimulation. Our work holds future-of-work implications for elevating creativity.

cs.SI↗

arXiv2021

Cues to gender and racial identity reduce creativity in diverse social networks

The characteristics of social partners have long been hypothesized as influential in guiding group interactions. Understanding how demographic cues impact networks of creative collaborators is critical for elevating creative performances therein. We conducted a randomized experiment to investigate how the knowledge of peers' gender and racial identities distorts people's connection patterns and the resulting creative outcomes in a dynamic social network. Consistent with prior work, we found that creative inspiration links are primarily formed with top idea-generators. However, when gender and racial identities are known, not only is there (1) an increase of 82.03% in the odds of same-gender connections (but not for same-race connections), but (2) the semantic similarity of idea-sets stimulated by these connections also increase significantly compared to demography-agnostic networks, negatively impacting the outcomes of divergent creativity. We found that ideas tend to be more homogeneous within demographic groups than between, taking away diversity-bonuses from similarity-based links and partly explaining the results. These insights can inform intelligent interventions to enhance network-wide creative performances.

cs.SI↗

arXiv2021

DBATES: DataBase of Audio features, Text, and visual Expressions in competitive debate Speeches

In this work, we present a database of multimodal communication features extracted from debate speeches in the 2019 North American Universities Debate Championships (NAUDC). Feature sets were extracted from the visual (facial expression, gaze, and head pose), audio (PRAAT), and textual (word sentiment and linguistic category) modalities of raw video recordings of competitive collegiate debaters (N=717 6-minute recordings from 140 unique debaters). Each speech has an associated competition debate score (range: 67-96) from expert judges as well as competitor demographic and per-round reflection surveys. We observe the fully multimodal model performs best in comparison to models trained on various compositions of modalities. We also find that the weights of some features (such as the expression of joy and the use of the word we) change in direction between the aforementioned models. We use these results to highlight the value of a multimodal dataset for studying competitive, collegiate debate.

cs.DB↗

arXiv2020

Technology-driven Alteration of Nonverbal Cues and its Effects on Negotiation

A person's appearance, identity, and other nonverbal cues can substantially influence how one is perceived by a negotiation counterpart, potentially impacting the outcome of the negotiation. With recent advances in technology, it is now possible to alter such cues through real-time video communication. In many cases, a person's physical presence can explicitly be replaced by 2D/3D representations in live interactive media. In other cases, technologies such as deepfake can subtly and implicitly alter many nonverbal cues -- including a person's appearance and identity -- in real-time. In this article, we look at some state-of-the-art technological advances that can enable such explicit and implicit alteration of nonverbal cues. We also discuss the implications of such technology for the negotiation landscape and highlight ethical considerations that warrant deep, ongoing attention from stakeholders.

cs.HC↗

arXiv2020

Creativity in temporal social networks: How divergent thinking is impacted by one's choice of peers

Creativity is viewed as one of the most important skills in the context of future-of-work. In this paper, we explore how the dynamic (self-organizing) nature of social networks impacts the fostering of creative ideas. We run 6 trials (N=288) of a web-based experiment involving divergent ideation tasks. We find that network connections gradually adapt to individual creative performances, as the participants predominantly seek to follow high-performing peers for creative inspirations. We unearth both opportunities and bottlenecks afforded by such self-organization. While exposure to high-performing peers is associated with better creative performances of the followers, we see a counter-effect that choosing to follow the same peers introduces semantic similarities in the followers' ideas. We formulate an agent-based simulation model to capture these intuitions in a tractable manner, and experiment with corner cases of various simulation parameters to assess the generality of the findings. Our findings may help design large-scale interventions to improve the creative aptitude of people interacting in a social network.

cs.SI↗