Advanced reasoning capabilities in Large Language Models (LLMs) have caused higher hallucination prevalence; yet most mitigation work focuses on after-the-fact filtering rather than shaping the queries that trigger them. We introduce QueryBandits, a bandit framework that designs rewrite strategies to maximize a reward model, that encapsulates hallucination propensity based upon the sensitivities of 17 linguistic features of the input query-and therefore, proactively steer LLMs away from generating hallucinations. Across 13 diverse QA benchmarks and 1,050 lexically perturbed queries per dataset, our top contextual QueryBandit (Thompson Sampling) achieves an 87.5% win rate over a no-rewrite baseline and also outperforms zero-shot static prompting ("paraphrase" or "expand") by 42.6% and 60.3% respectively. Therefore, we empirically substantiate the effectiveness of QueryBandits in mitigating hallucination via the intervention that takes the form of a query rewrite. Interestingly, certain static prompting strategies, which constitute a considerable number of current query rewriting literature, have a higher cumulative regret than the no-rewrite baseline, signifying that static rewrites can worsen hallucination. Moreover, we discover that the converged per-arm regression feature weight vectors substantiate that there is no single rewrite strategy optimal for all queries. In this context, guided rewriting via exploiting semantic features with QueryBandits can induce significant shifts in output behavior through forward-pass mechanisms, bypassing the need for retraining or gradient-based adaptation.

Artificial Intelligence (AI) is increasingly used in hiring, with large language models (LLMs) having the potential to influence or even make hiring decisions. However, this raises pressing concerns about bias, fairness, and trust, particularly across diverse cultural contexts. Despite their growing role, few studies have systematically examined the potential biases in AI-driven hiring evaluation across cultures. In this study, we conduct a systematic analysis of how LLMs assess job interviews across cultural and identity dimensions. Using two datasets of interview transcripts, 100 from UK and 100 from Indian job seekers, we first examine cross-cultural differences in LLM-generated scores for hirability and related traits. Indian transcripts receive consistently lower scores than UK transcripts, even when they were anonymized, with disparities linked to linguistic features such as sentence complexity and lexical diversity. We then perform controlled identity substitutions (varying names by gender, caste, and region) within the Indian dataset to test for name-based bias. These substitutions do not yield statistically significant effects, indicating that names alone, when isolated from other contextual signals, may not influence LLM evaluations. Our findings underscore the importance of evaluating both linguistic and social dimensions in LLM-driven evaluations and highlight the need for culturally sensitive design and accountability in AI-assisted hiring.

We analyzed nearly 460,000 AI model cards from Hugging Face to examine how developers report risks. From these, we extracted around 3,000 unique risk mentions and built the \emph{AI Model Risk Catalog}. We compared these with risks identified by researchers in the MIT Risk Repository and with real-world incidents from the AI Incident Database. Developers focused on technical issues like bias and safety, while researchers emphasized broader social impacts. Both groups paid little attention to fraud and manipulation, which are common harms arising from how people interact with AI. Our findings show the need for clearer, structured risk reporting that helps developers think about human-interaction and systemic risks early in the design process. The catalog and paper appendix are available at: https://social-dynamics.net/ai-risks/catalog.

This research paper examines, from a multidimensional perspective (cognitive, social, ethical, and philosophical), how AI is transforming human thought. It highlights a cognitive offloading effect: the externalization of mental functions to AI can reduce intellectual engagement and weaken critical thinking. On the social level, algorithmic personalization creates filter bubbles that limit the diversity of opinions and can lead to the homogenization of thought and polarization. This research also describes the mechanisms of algorithmic manipulation (exploitation of cognitive biases, automated disinformation, etc.) that amplify AI's power of influence. Finally, the question of potential artificial consciousness is discussed, along with its ethical implications. The report as a whole underscores the risks that AI poses to human intellectual autonomy and creativity, while proposing avenues (education, transparency, governance) to align AI development with the interests of humanity.

Social identity theory (SIT) and social categorization theory (SCT) are two facets of the social identity approach (SIA) to understanding social phenomena. SIT and SCT are models that describe and explain how people interact with one another socially, connecting the individual to the group through an understanding of underlying psychological mechanisms and intergroup behaviour. SIT, originally developed in the 1970s, and SCT, a later, more general offshoot, have been broadly applied to a range of social phenomena among people. The rise of increasingly social machines embedded in daily life has spurned efforts on understanding whether and how artificial agents can and do participate in SIA activities. As agents like social robots and chatbots powered by sophisticated large language models (LLMs) advance, understanding the real and potential roles of these technologies as social entities is crucial. Here, I provide a primer on SIA and extrapolate, through case studies and imagined examples, how SIT and SCT can apply to artificial social agents. I emphasize that not all human models and sub-theories will apply. I further argue that, given the emerging competence of these machines and our tendency to be taken in by them, we experts may need to don the hat of the uncanny killjoy, for our own good.

Urban land-use allocation represents a complex multi-objective optimization problem critical for sustainable urban development policy. This paper presents novel computational intelligence approaches for optimizing land-use allocation in mixed-use areas, addressing inherent trade-offs between land-use compatibility and economic objectives. We develop multiple optimization algorithms, including custom variants integrating differential evolution with multi-objective genetic algorithms. Key contributions include: (1) CR+DES algorithm leveraging scaled difference vectors for enhanced exploration, (2) systematic constraint relaxation strategy improving solution quality while maintaining feasibility, and (3) statistical validation using Kruskal-Wallis tests with compact letter displays. Applied to a real-world case study with 1,290 plots, CR+DES achieves 3.16\% improvement in land-use compatibility compared to state-of-the-art methods, while MSBX+MO excels in price optimization with 3.3\% improvement. Statistical analysis confirms algorithms incorporating difference vectors significantly outperform traditional approaches across multiple metrics. The constraint relaxation technique enables broader solution space exploration while maintaining practical constraints. These findings provide urban planners and policymakers with evidence-based computational tools for balancing competing objectives in land-use allocation, supporting more effective urban development policies in rapidly urbanizing regions.

Tool-augmented large language models (LLMs) leverage external functions to extend their capabilities, but inaccurate function calls can lead to inefficiencies and increased costs.Existing methods address this challenge by fine-tuning LLMs or using demonstration-based prompting, yet they often suffer from high training overhead and fail to account for inconsistent demonstration samples, which misguide the model's invocation behavior. In this paper, we trained a behavior-aligned retriever (BAR), which provides behaviorally consistent demonstrations to help LLMs make more accurate tool-using decisions. To train the BAR, we construct a corpus including different function-calling behaviors, i.e., calling or non-calling.We use the contrastive learning framework to train the BAR with customized positive/negative pairs and a dual-negative contrastive loss, ensuring robust retrieval of behaviorally consistent examples.Experiments demonstrate that our approach significantly reduces erroneous function calls while maintaining high task performance, offering a cost-effective and efficient solution for tool-augmented LLMs.

Multi-turn interactions with language models (LMs) pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and diversity remain among the key challenges of multi-turn red-teaming. To address these challenges, we present X-Teaming, a scalable framework that systematically explores how seemingly harmless interactions escalate into harmful outcomes and generates corresponding attack scenarios. X-Teaming employs collaborative agents for planning, attack optimization, and verification, achieving state-of-the-art multi-turn jailbreak effectiveness and diversity with success rates up to 98.1% across representative leading open-weight and closed-source models. In particular, X-Teaming achieves a 96.2% attack success rate against the latest Claude 3.7 Sonnet model, which has been considered nearly immune to single-turn attacks. Building on X-Teaming, we introduce XGuard-Train, an open-source multi-turn safety training dataset that is 20x larger than the previous best resource, comprising 30K interactive jailbreaks, designed to enable robust multi-turn safety alignment for LMs. Our work offers essential tools and insights for mitigating sophisticated conversational attacks, advancing the multi-turn safety of LMs.

Elon Musk's artificial intelligence startup xAI has sued Apple and ChatGPT maker OpenAI, accusing them of illegally conspiring to thwart competition for artificial intelligence (AI). The lawsuit filed in a United States federal court in Texas on Monday says that Apple and OpenAI have "locked up markets to maintain their monopolies and prevent innovators like X and xAI from competing". The complaint filed by the billionaire said Apple and OpenAI conspired to suppress xAI's products, including on the Apple App Store. "If not for its exclusive deal with OpenAI, Apple would have no reason to refrain from more prominently featuring the X app and the Grok app in its App Store," xAI said. The lawsuit pointed out that in June 2024, Apple and OpenAI announced they would integrate ChatGPT into Apple's operating system under an exclusive arrangement.

Elon Musk's artificial intelligence startup xAI is suing OpenAI and Apple over allegations that they are engaging in anticompetitive conduct. The lawsuit, filed in a Texas court on Monday, accuses the companies of "a conspiracy to monopolize the markets for smartphones and generative AI chatbots". Musk had earlier this month threatened to sue Apple and OpenAI, which makes ChatGPT, after claiming that Apple was "making it impossible" for any other AI companies to reach the top spot on its app store. Musk's xAI makes the Grok chatbot, which has struggled to become as prominent as ChatGPT. Musk's lawsuit challenges a key partnership between Apple and OpenAI that was announced last year, in which the device maker integrated OpenAI's artificial intelligence capabilities into its operating systems.