相关论文: Are Personalized Stochastic Parrots More Dangerous…
Dialogue systems in the form of chatbots and personal assistants are being increasingly integrated into people's lives. Modern dialogue systems may consider adopting anthropomorphic personas, mimicking societal demographic groups to appear…
Persona-assigned large language models (LLMs) are used in domains such as education, healthcare, and sociodemographic simulation. Yet, they are typically evaluated only in short, single-round settings that do not reflect real-world usage.…
Automated dialogue or conversational systems are anthropomorphised by developers and personified by users. While a degree of anthropomorphism may be inevitable due to the choice of medium, conscious and unconscious design choices can guide…
Personalized dialogue systems have advanced considerably with the integration of user-specific personas into large language models (LLMs). However, while LLMs can effectively generate personalized responses, the influence of persona…
Large Language Models (LLMs) are increasingly deployed in interactions where they are prompted to adopt personas. This paper investigates whether such persona conditioning affects model safety under bullying, an adversarial manipulation…
Endowing a dialogue system with particular personality traits is essential to deliver more human-like conversations. However, due to the challenge of embodying personality via language expression and the lack of large-scale persona-labeled…
Narrative systems, such as dialogue and storytelling systems, often utilize persona profiles to enhance personalized interactions. Existing persona profiles frequently exhibit biases, posing risks to system integrity and fairness. To…
Recent Large Language Model (LLM) based AI can exhibit recognizable and measurable personality traits during conversations to improve user experience. However, as human understandings of their personality traits can be affected by their…
Large language models (LLMs) have shown incredible capabilities and transcended the natural language processing (NLP) community, with adoption throughout many services like healthcare, therapy, education, and customer service. Since users…
The research of open-domain dialog systems has been greatly prospered by neural models trained on large-scale corpora, however, such corpora often introduce various safety problems (e.g., offensive languages, biases, and toxic behaviors)…
Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This \textit{motivated reasoning} at a collective level can be detrimental to society when…
Technology for open-ended language generation, a key application of artificial intelligence, has advanced to a great extent in recent years. Large-scale language models, which are trained on large corpora of text, are being used in a wide…
All AI models are susceptible to learning biases in data that they are trained on. For generative dialogue models, being trained on real human conversations containing unbalanced gender and race/ethnicity references can lead to models that…
Persona prompting is increasingly used in large language models (LLMs) to simulate views of various sociodemographic groups. However, how a persona prompt is formulated can significantly affect outcomes, raising concerns about the fidelity…
Warning: This research studies AI persuasion and bias amplification that could be misused; all experiments are for safety evaluation. Large Language Models (LLMs) now generate convincing, human-like text and are widely used in content…
Models trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior and unwanted biases. We investigate a variety of methods to mitigate these…
Current works in the generation of personalized dialogue primarily contribute to the agent presenting a consistent personality and driving a more informative response. However, we found that the generated responses from most previous models…
The use of dialogue systems as a medium for human-machine interaction is an increasingly prevalent paradigm. A growing number of dialogue systems use conversation strategies that are learned from large datasets. There are well documented…
Large language models increasingly serve as conversational agents that adopt personas and role-play characters at user request. This capability, while valuable, raises concerns about sycophancy: the tendency to provide responses that…
Endowing dialogue systems with personas is essential to deliver more human-like conversations. However, this problem is still far from well explored due to the difficulties of both embodying personalities in natural languages and the…