相关论文: PICon: A Multi-Turn Interrogation Framework for Ev…

Maintaining persona consistency is paramount in the application of open-domain dialogue systems, as exemplified by models like ChatGPT. Despite significant advancements, the limited scale and diversity of current persona dialogue datasets…

Large language models (LLMs) increasingly reach real-world applications, necessitating a better understanding of their behaviour. Their size and complexity complicate traditional assessment methods, causing the emergence of alternative…

As large language models are increasingly integrated into education, virtual student agents are becoming vital for classroom simulation and teacher training. Yet their classroom-oriented subjective abilities remain largely unassessed,…

From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a…

Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail of their intent, practical web agents must be able to interpret ambiguous queries by inferring…

Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks. Recent studies have explored human-like problem-solving strategies, such as…

Run the same LLM agent on the same task twice: do you get the same behavior? We find the answer is often no. In a study of 3,000 agent runs across three models (Llama 3.1 70B, GPT-4o, and Claude Sonnet 4.5) on HotpotQA, we observe that…

People's opinions on a wide range of topics often evolve over time through their interactions with others. Models of opinion dynamics primarily focus on one-dimensional opinions, which represent opinions on one topic. However, opinions on…

Consistency is a fundamental dimension of trustworthiness in Large Language Models (LLMs). For humans to be able to trust LLM-based applications, their outputs should be consistent when prompted with inputs that carry the same meaning or…

Large Language Models (LLMs) exhibit remarkable fluency and competence across various natural language tasks. However, recent research has highlighted their sensitivity to variations in input prompts. To deploy LLMs in a safe and reliable…

While confidence estimation is a promising direction for mitigating hallucinations in Large Language Models (LLMs), current research overwhelmingly focuses on single-turn settings. The dynamics of model confidence in multi-turn…

Large Language Models (LLMs) are exhibiting emergent human-like abilities and are increasingly envisioned as the foundation for simulating an individual's communication style, behavioral tendencies, and personality traits. However, current…

Deception is a pervasive feature of human communication and an emerging concern in large language models (LLMs). While recent studies document instances of LLM deception, most evaluations remain confined to single-turn prompts and fail to…

Large Language Model (LLM)-based multi-agent systems are increasingly applied to automate computational workflows in science and engineering. However, how inter-agent dynamics influence reasoning quality and verification reliability remains…

Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the…

What does it mean to model a person, not merely to predict isolated responses, preferences, or behaviors, but to simulate how an individual interprets events, forms opinions, makes judgments, and acts consistently across contexts? This…

Large Language Models (LLMs) are increasingly used in settings where reliable self-assessment is critical. Assessing model reliability has evolved from using probabilistic correctness estimates to, more recently, eliciting verbalized…

We propose a multi-agent framework for modeling artificial consciousness in large language models (LLMs), grounded in psychoanalytic theory. Our \textbf{Psychodynamic Model} simulates self-awareness, preconsciousness, and unconsciousness…

Recent advances in multimodal question answering have primarily focused on combining heterogeneous modalities or fine-tuning multimodal large language models. While these approaches have shown strong performance, they often rely on a…

As large language models (LLMs) are increasingly used in human-centered tasks, assessing their psychological traits is crucial for understanding their social impact and ensuring trustworthy AI alignment. While existing reviews have covered…