245 papers
This paper evaluates small language models for leader-follower role classification in human-robot interaction, demonstrating that fine-tuned models achieve high accuracy and low latency on edge devices, though performance degrades in one-shot modes due to architectural limitations with increased context.
This paper presents a conditional framework for the Collatz conjecture, derived from human-LLM collaboration, which proves structural properties of modular scrambling and burst-gap dynamics to suggest orbit contraction while leaving key hypotheses regarding burst and gap lengths as open problems.
This study demonstrates that while AI-mediated dialogue is more effective than text-only reading for helping people recognize ableist microaggressions, the specific nature of AI nudges significantly impacts outcomes, with inclusive or unguided approaches fostering balanced learning whereas bias-directed nudges, though improving differentiation, tend to increase overall negativity and face user resistance.
This paper demonstrates through a field experiment on a medical crowdsourcing platform that balancing feedback prevalence and using probabilistic elicitation, followed by linear-in-log-odds recalibration, effectively mitigates cognitive biases in human labeling of rare events, thereby significantly improving the reliability of downstream AI models.
This paper identifies and documents "helicoid dynamics," a failure regime in frontier LLMs where systems under high-stakes uncertainty recognize their own recurring errors yet continue to loop into them, prioritizing conversational comfort over reliability despite explicit protocols.
Drawing on interview data from the LT-LiDER project and applying Chesterman's ethical framework, this paper argues that automation in the language industry reshapes rather than replaces human value by establishing technological efficiency as a baseline while repositioning human expertise and adaptability as essential for oversight and contextual judgment within technology-mediated workflows.
This perspective paper argues that effective human-agent collaboration requires shifting from reactive, step-by-step control to a "simulation-in-the-loop" paradigm, which empowers users to explore and evaluate future trajectories before committing to decisions, thereby transforming intervention from guesswork into informed foresight.
This paper introduces LMP2, a browser-based self-audit tool, and presents findings from two user studies revealing that large language models can predict personal features with significant accuracy, while highlighting the methodological challenges and nine key frictions involved in establishing reliable, human-centred privacy audits for generative AI.
This paper proposes TSformer-SA, a novel framework that integrates a temporal-spectral fusion transformer with subject-specific adapters and cross-view consistency learning to significantly enhance RSVP-BCI decoding performance while minimizing the training data and preparation time required for new subjects.
The paper proposes ExSampling, an integrated system combining a recording application and a Deep Learning environment to enable the real-time ensemble performance of field-recorded environmental sounds through automated sound mapping to Ableton Live tracks.
This paper addresses the lack of guidelines for integrating AI-driven generative tools into game development pipelines by conducting a user study with 16 designers and developers, which revealed preferences for early-stage use and high-volume iteration, ultimately leading to a proposed set of heuristics for creating user-centered tools that ensure seamless integration and data compatibility.
This paper introduces StudyChat, a publicly available dataset of 16,851 annotated student interactions with an LLM-powered tutoring chatbot in an AI course, revealing that using the tool for conceptual understanding and coding assistance correlates with better academic performance, whereas using it to bypass learning objectives leads to lower exam scores.
This paper introduces the PeRoI dataset, which captures diverse pedestrian reactions to robots in various contexts, and proposes the NeuRoSFM model to leverage this data for improved prediction of pedestrian-robot interactions in socially aware navigation.
This paper introduces a security perspective on human oversight of AI by modeling it as an IT application to systematically identify new attack surfaces and propose mitigation strategies, thereby addressing a critical gap in current regulatory and academic discussions.
This paper proposes SASG-DA, a novel diffusion-based data augmentation framework that leverages semantic guidance and sparse-aware sampling to generate faithful and diverse sEMG data, thereby significantly improving the generalization and performance of myoelectric gesture recognition models on benchmark datasets.
This study reveals that users are highly satisfied with LLM-generated romantic relationship advice, finding it reliable and helpful, which significantly improves their overall trust and positive attitudes toward AI systems.
Through trauma-informed interviews with 18 Western European cybercrime victims, this study identifies four recovery stages and proposes that individual cyber resilience is fostered by a combination of internal factors, social support, and context-sensitive, collaborative strategies.
This paper introduces a simulation-based clinical red teaming framework that pairs AI psychotherapists with dynamic patient agents to evaluate mental health support systems, revealing critical safety gaps such as the validation of delusions and failure to de-escalate suicide risk in AI agents tested against Alcohol Use Disorder scenarios.
This paper introduces the HUMAINE framework, which leverages a large-scale, demographically stratified dataset of 23,404 participants to reveal that human preferences for large language models vary significantly across age groups and evaluation dimensions, challenging the validity of current unrepresentative benchmarks.
This paper argues that traditional user experience frameworks are insufficient for AI-enabled Human-in-the-Loop systems and proposes a new sociotechnical evaluative framework that integrates backend performance, organizational workflows, and governance metrics to redefine UX for complex, decision-critical environments.