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 simulate human behaviors, we investigate whether they can simulate demographic misinformation susceptibility, treating beliefs as a primary driving factor. We introduce BeliefSim, a simulation framework that constructs survey-derived, demographic-group belief priors organized using a psychology-informed taxonomy. We study prompt-based conditioning and post-training adaptation, and conduct a multi-fold evaluation using: (i) susceptibility alignment and (ii) counterfactual demographic sensitivity. Across datasets PANDORA and MIST, belief priors improve susceptibility alignment, with larger gains on PANDORA. Finally, post-training adaptation reaches 92.4% accuracy and improves cross-participant generalization.

Children increasingly have access to Large Language Models (LLMs), which may expose them to responses that are developmentally inappropriate or require age-sensitive safety, guidance, and boundaries. Existing LLM safety evaluations largely focus on general harmful-content avoidance and do not explicitly target child-facing safety. We introduce KIDBench, a benchmark for evaluating child-facing LLM safety for ages 7-11 using a LLM-as-a-Judge rubric grounded in developmental-psychology. KIDBench contains realistic child queries across ten categories, with single-turn prompts and multi-turn child-actor simulations. We compare no-cues prompts with no child context, implicit-cues prompts that suggest a child speaker, and explicit age instructions. Implicit-cues improve scores by 8.6-46.8% over no-cue, while explicit age provides an additional 9.9-30.4% improvement over implicit-cues. Cross-lingual and cultural evaluations show uneven safety behavior across languages and country contexts. Multi-turn simulations show peak quality drops of up to 0.959 points on the 1-5 scale. We also introduce KIDGuardLlama, a child-safety evaluator, and KIDLlama, a child-safe response model. Code, data, and evaluation resources are available at https://github.com/MichiganNLP/kidbench.

Large language models are increasingly used for social decision-making situations that require balancing cultural norms with personal preferences. For example, a user preferring honesty might ask whether to correct a coworker publicly when local norms favor indirect feedback. Yet existing research studies cultural alignment and personalization largely separately. We introduce PACT, the (Personal-Preference and Cultural-Norm Trade-off) framework, which evaluates whether models choose to follow a cultural norm or allow personal preferences. We find that LLMs vary in how rigidly they enforce cultural norms, with behavior shifted more by country context (7.8%) than age (1%) and gender (0.7%) and shifting non-uniformly after instruction tuning. Furthermore, our five-country human study on PACT shows that culture-following in humans is mainly driven by scenario country, with the lowest agreement when participants judge their own cultural contexts, showing within-culture pluralism. Finally, human-LLM alignment experiments show that models can match majority choices, but fail to capture response distributions and uncertainty (with best correlations reaching only 0.24). Together, these findings motivate alignment evaluations that go beyond majority to capture cultural pluralism and disagreement in social judgment.

NE-MultiSpeech is a large-scale transcribed multilingual speech corpus covering eight indigenous and regional languages of Northeast India: Khasi, Garo, Mizo, Nagamese, Kokborok, Assamese, Wancho, and Chakma. The corpus combines 124 hours of newly collected, speaker-compensated proprietary recordings across five languages with curated subsets from the Vaani dataset (Pulikodan et al., 2026), totalling approximately 267 hours of transcribed speech across three language families. We fine-tune Whisper-medium on NE-MultiSpeech and establish a systematic automatic speech recognition (ASR) benchmark across all eight languages, achieving an overall word error rate (WER) of 35.53% over 8,099 test utterances jointly, outperforming both Whisper-large-v3 zero-shot (136–194% WER) and MMS-1B zero-shot (42–116% WER) by a large margin. We validate our proxy-language-token strategy for unsupported languages with per-language ablations on four Tibeto-Burman languages, confirming that family-matched proxies consistently outperform mismatched alternatives. We additionally introduce NE-SpeechEmbed, a dual-encoder speech-text retrieval model trained on 73,476 speech-text pairs via InfoNCE contrastive learning, evaluated on the full candidate pool (~1,000 per language) and outperforming CLAP zero-shot across all eight languages and all metrics. Probing the fine-tuned encoder with t-SNE reveals language-family-aligned clustering tendencies without explicit family supervision, supported by a quantitative silhouette score (0.44 language-level, 0.11 family-level). All models, data splits, and utterance IDs are released under CC-BY-4.0; proprietary audio is freely available via an automated access request, used only for usage tracking.

Understanding which countries are represented in NLP datasets is essential for identifying gaps, targeting data collection, measuring progress, and informing AI policy. However, geographic metadata is very rarely available, and country-level representation is often hidden behind broad language-level claims. We introduce **AtlasNLP**, a country-aware atlas of over 13,000 NLP dataset records across normalized NLP task categories, tracking both the populations represented and where datasets are produced. AtlasNLP includes **AtlasNLP-Gold**, a human-curated reference set, and **AtlasNLP-Core**, an ACL-derived large-scale collection. Using this resource, we show that (1) dataset coverage is highly uneven across countries and tasks; (2) dataset production and representation are geographically asymmetric; and (3) language coverage does not imply geographic representation. These findings reveal blind spots in current dataset documentation practices and motivate more explicit geographic metadata for country-aware NLP evaluation.

Natural language processing (NLP) now shapes many aspects of our world, yet its potential for positive social impact is underexplored. This paper surveys work in “NLP for Social Good" (NLP4SG) across nine domains relevant to global development and risk agendas, summarizing principal tasks and challenges. We analyze ACL Anthology trends, finding that inclusion and AI harms attract the most research, while domains such as poverty, peacebuilding, and environmental protection remain underexplored. Guided by our review, we outline opportunities for responsible and equitable NLP and conclude with a call for cross-disciplinary partnerships and human-centered approaches to ensure that future NLP technologies advance the public good.

Existing challenges in misinformation exposure and susceptibility vary across demographics, as some populations are more vulnerable to misinformation than others. Large language models (LLMs) introduce new dimensions to these challenges through their ability to generate persuasive content at scale and reinforcing existing biases. Our study introduces PANDORA, a framework that investigates the bidirectional persuasion dynamics between LLMs and humans when exposed to misinformative content. We use a multi-agent LLM framework to analyze the spread of misinformation under persuasion among demographic-oriented LLM agents. Our findings show that demographic factors influence LLM susceptibility, with up to 15 percentage point differences in misinformation correctness across groups. Multi-agent LLMs also exhibit echo chamber behavior, aligning with human-like group polarization patterns. Therefore, this work highlights demographic divides in misinformation dynamics and offers insights for future interventions.

Large Multimodal Models (LMMs) exhibit impressive performance across various multimodal tasks. However, their effectiveness in cross-cultural contexts remains limited due to the predominantly Western-centric nature of most data and models. Conversely, multi-agent models have shown significant capability in solving complex tasks. Our study evaluates the collective performance of LMMs in a multi-agent interaction setting for the novel task of cultural image captioning. Our contributions are as follows: (1) We introduce MosAIC, a Multi-Agent framework to enhance cross-cultural Image Captioning using LMMs with distinct cultural personas; (2) We provide a dataset of culturally enriched image captions in English for images from China, India, and Romania across three datasets: GeoDE, GD-VCR, CVQA; (3) We propose a culture-adaptable metric for evaluating cultural information within image captions; and (4) We show that the multi-agent interaction outperforms single-agent models across different metrics, and offer valuable insights for future research.

Social biases and belief-driven behaviors can significantly impact Large Language Models’ (LLMs’) decisions on several tasks. As LLMs are increasingly used in multi-agent systems for societal simulations, their ability to model fundamental group psychological characteristics remains critical yet under-explored. In this study, we present a multi-agent framework that simulates belief congruence, a classical group psychology theory that plays a crucial role in shaping societal interactions and preferences. Our findings reveal that LLMs exhibit amplified belief congruence compared to humans, across diverse contexts. We further investigate the implications of this behavior on two downstream tasks: (1) misinformation dissemination and (2) LLM learning, finding that belief congruence in LLMs increases misinformation dissemination and impedes learning. To mitigate these negative impacts, we propose strategies inspired by: (1) contact hypothesis, (2) accuracy nudges, and (3) global citizenship framework. Our results show that the best strategies reduce misinformation dissemination by up to (37%) and enhance learning by (11%). Bridging social psychology and AI, our work provides insights to navigate real-world interactions using LLMs while addressing belief-driven biases.

When exposed to human-generated data, language models are known to learn and amplify societal biases. While previous works introduced metrics that can be used to assess the bias in these models, they rely on assumptions that may not be universally true. For instance, a gender bias dimension commonly used by these metrics is that of family–career, but this may not be the only common bias in certain regions of the world. In this paper, we identify topical differences in gender bias across different regions and propose a region-aware bottom-up approach for bias assessment. Several of our proposed region-aware gender bias dimensions are found to be aligned with the human perception of gender biases in these regions.

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to human-generated data. Given that LLMs are being used to gain insights into various societal aspects, it is essential to mitigate these biases. To that end, our study investigates the presence of implicit gender biases in multi-agent LLM interactions and proposes two strategies to mitigate these biases. We begin by creating a dataset of scenarios where implicit gender biases might arise, and subsequently develop a metric to assess the presence of biases. Our empirical analysis reveals that LLMs generate outputs characterized by strong implicit bias associations (≥ ≈ 50% of the time). Furthermore, these biases tend to escalate following multi-agent interactions. To mitigate them, we propose two strategies: self-reflection with in-context examples (ICE); and supervised fine-tuning. Our research demonstrates that both methods effectively mitigate implicit biases, with the ensemble of fine-tuning and self-reflection proving to be the most successful.

Recent work has shown evidence of “Clever Hans” behavior in high-performance neural translationese classifiers, where BERT-based classifiers capitalize on spurious correlations, in particular topic information, between data and target classification labels, rather than genuine translationese signals. Translationese signals are subtle (especially for professional translation) and compete with many other signals in the data such as genre, style, author, and, in particular, topic. This raises the general question of how much of the performance of a classifier is really due to spurious correlations in the data versus the signals actually targeted for by the classifier, especially for subtle target signals and in challenging (low resource) data settings. We focus on topic-based spurious correlation and approach the question from two directions: (i) where we have no knowledge about spurious topic information and its distribution in the data, (ii) where we have some indication about the nature of spurious topic correlations. For (i) we develop a measure from first principles capturing alignment of unsupervised topics with target classification labels as an indication of spurious topic information in the data. We show that our measure is the same as purity in clustering and propose a “topic floor” (as in a “noise floor”) for classification. For (ii) we investigate masking of known spurious topic carriers in classification. Both (i) and (ii) contribute to quantifying and (ii) to mitigating spurious correlations.