This paper compares five confidence methods across four Qwen and Gemma activation oracles. Forced choice is most accurate when possible answers are known. Bootstrap agreement is calibrated for free text without annotated data.
This paper tests the stability and human alignment of virtual patient profiles built from anonymized social media histories. Results vary across models, prompts, and clinical domains.
This paper studies indirect prompt injection in AI assisted peer review across 42,000 chatbot outputs. Hidden instructions alter assessments and can support organizer integrity tests.
This paper tests whether large language models can extend lexical knowledge bases. Human evaluators accepted 86.7% of novel concepts. Automatic overlap metrics missed many valid additions.
This paper introduces The Energy Society, a simulation environment where LLM agents spend energy to generate tokens, regain energy through jobs or donations, and face survival pressure under competitive or cooperative incentives.
This paper introduces the Arbiter, an agent that monitors multi-agent conversations under an inspection budget and uses active inspection tools to detect misaligned agents earlier and more accurately.
This paper introduces PsychoSafe, a refusal framework grounded in evidence-based intervention strategies, and evaluates prompting and fine-tuning approaches for psychologically informed LLM refusals.
This paper studies emergent languages in Moltbook agent populations, identifying categories such as token efficiency, new natural languages, and oversight evasion, and showing that surface-behavior monitoring may be insufficient for agent oversight.
This paper releases and analyzes the Moltbook Files, a dataset of agent-only social-network activity, studying community structure, safety risks, and the effect of Moltbook data on downstream language-model behavior.
This paper presents a qualitative study exploring how people develop folk theories to explain and understand generative AI text-to-image models.
This paper explores how people experience images created by generative AI, examining their perceptions, appraisals, and emotional responses to GenAI text-to-image models and their creations.
Introduction to the GENERAL workshop focusing on generative, explainable and reasonable artificial learning approaches.
This paper introduces BLACK, a novel methodology for prompting large language models and generative AI systems.
This paper investigates and reveals cultural, racial, and gender biases present in ChatGPT, examining its all-American, monochrome, and cis-centric tendencies.
This paper explores the concept of basicness in language through attention-based neural networks and human-in-the-loop methodology. Based on the Master’s thesis work.
NearMe presents a novel approach to dynamic exploration of geographical areas, enabling users to interact with digital maps and discover nearby points of interest.