中文
相关论文

相关论文: Are Personalized Stochastic Parrots More Dangerous…

200 篇论文

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…

计算与语言 · 计算机科学 2021-12-16 Emily Sheng , Josh Arnold , Zhou Yu , Kai-Wei Chang , Nanyun Peng

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…

计算与语言 · 计算机科学 2023-10-24 Gavin Abercrombie , Amanda Cercas Curry , Tanvi Dinkar , Verena Rieser , Zeerak Talat

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…

计算与语言 · 计算机科学 2025-06-03 Yonghyun Jun , Hwanhee Lee

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…

人工智能 · 计算机科学 2025-05-20 Ziwei Xu , Udit Sanghi , Mohan Kankanhalli

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…

计算与语言 · 计算机科学 2020-01-03 Yinhe Zheng , Guanyi Chen , Minlie Huang , Song Liu , Xuan Zhu

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…

计算与语言 · 计算机科学 2025-01-03 Kuiyun Chen , Yanbin Wei

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…

人机交互 · 计算机科学 2026-01-21 Jingshu Li , Tianqi Song , Nattapat Boonprakong , Zicheng Zhu , Yitian Yang , Yi-Chieh Lee

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…

计算与语言 · 计算机科学 2023-04-12 Ameet Deshpande , Vishvak Murahari , Tanmay Rajpurohit , Ashwin Kalyan , Karthik Narasimhan

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)…

计算与语言 · 计算机科学 2022-10-31 Jingyan Zhou , Jiawen Deng , Fei Mi , Yitong Li , Yasheng Wang , Minlie Huang , Xin Jiang , Qun Liu , Helen Meng

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…

人工智能 · 计算机科学 2026-04-20 Saloni Dash , Amélie Reymond , Emma S. Spiro , Aylin Caliskan

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…

计算与语言 · 计算机科学 2023-05-12 Saketh Reddy Karra , Son The Nguyen , Theja Tulabandhula

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…

计算与语言 · 计算机科学 2021-09-09 Eric Michael Smith , Adina Williams

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…

计算与语言 · 计算机科学 2025-10-06 Marlene Lutz , Indira Sen , Georg Ahnert , Elisa Rogers , Markus Strohmaier

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…

计算与语言 · 计算机科学 2025-08-25 Saumya Roy

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…

计算与语言 · 计算机科学 2021-08-06 Jing Xu , Da Ju , Margaret Li , Y-Lan Boureau , Jason Weston , Emily Dinan

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…

计算与语言 · 计算机科学 2022-08-23 Itsugun Cho , Dongyang Wang , Ryota Takahashi , Hiroaki Saito

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…

计算与语言 · 计算机科学 2026-04-14 Arya Shah , Deepali Mishra , Chaklam Silpasuwanchai

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…

计算与语言 · 计算机科学 2019-11-13 Yinhe Zheng , Rongsheng Zhang , Xiaoxi Mao , Minlie Huang
‹ 上一页 1 2 3 10 下一页 ›