English
Related papers

Related papers: I'm Afraid I Can't Do That: Predicting Prompt Refu…

200 papers

This article presents a comparative analysis of the ability of two large language model (LLM)-based chatbots, ChatGPT and Bing Chat, recently rebranded to Microsoft Copilot, to detect veracity of political information. We use AI auditing…

Computation and Language · Computer Science 2023-12-21 Elizaveta Kuznetsova , Mykola Makhortykh , Victoria Vziatysheva , Martha Stolze , Ani Baghumyan , Aleksandra Urman

Previous discussions have highlighted the need for generative AI tools to become more culturally sensitive, yet often neglect the complexities of handling content about minorities, who are perceived differently across cultures and…

Computers and Society · Computer Science 2026-01-27 Lilla Vicsek , Anna Vancsó , Mike Zajko , Judit Takacs

The rapid evolution of artificial intelligence (AI), specifically large language models (LLMs), has opened opportunities for various educational applications. This paper explored the feasibility of utilizing ChatGPT, one of the most popular…

Human-Computer Interaction · Computer Science 2023-12-20 Zhengdong Zhang , Zihan Dong , Yang Shi , Noboru Matsuda , Thomas Price , Dongkuan Xu

Background: The integration of artificial intelligence (AI) into daily life, particularly through chatbots utilizing natural language processing (NLP), presents both revolutionary potential and unique challenges. This intended to…

Computation and Language · Computer Science 2024-04-16 Gian Alexandre Michaelsen , Renato P. dos Santos

Safety guardrails in large language models(LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to…

Computation and Language · Computer Science 2025-11-03 Adel Khorramrouz , Sharon Levy

The challenge of formal proof generation has a rich history, but with modern techniques, we may finally be at the stage of making actual progress in real-life mathematical problems. This paper explores the integration of ChatGPT and basic…

Logic in Computer Science · Computer Science 2025-02-20 Sangjun Han , Taeil Hur , Youngmi Hur , Kathy Sangkyung Lee , Myungyoon Lee , Hyojae Lim

One fundamental question for the social sciences today is: how much can we trust highly complex predictive models like ChatGPT? This study tests the hypothesis that subtle changes in the structure of prompts do not produce significant…

Generative pretraining (the "GPT" in ChatGPT) enables language models to learn from vast amounts of internet text without human supervision. This approach has driven breakthroughs across AI by allowing deep neural networks to learn from…

Neurons and Cognition · Quantitative Biology 2025-09-23 Thomas Serre , Ellie Pavlick

Generative language models, such as ChatGPT, have garnered attention for their ability to generate human-like writing in various fields, including academic research. The rapid proliferation of generated texts has bolstered the need for…

Computation and Language · Computer Science 2023-12-19 Vikas Kumar , Amisha Bharti , Devanshu Verma , Vasudha Bhatnagar

Educational chatbots come with a promise of interactive and personalized learning experiences, yet their development has been limited by the restricted free interaction capabilities of available platforms and the difficulty of encoding…

With the release of ChatGPT in 2022, generative AI has significantly lowered the cost of polishing and rewriting text. Due to its widespread usage, conference organizers instated specific requirements researchers need to adhere to when…

Cryptography and Security · Computer Science 2026-04-13 Daan Vansteenhuyse

In November 2022, OpenAI has introduced ChatGPT, a chatbot based on supervised and reinforcement learning. Not only can it answer questions emulating human-like responses, but it can also generate code from scratch or complete coding…

Human-Computer Interaction · Computer Science 2024-02-01 Dan-Matei Popovici

Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish different refusal types before responding. In this work, we…

Artificial Intelligence · Computer Science 2026-03-17 Rishab Alagharu , Ishneet Sukhvinder Singh , Shaibi Shamsudeen , Zhen Wu , Ashwinee Panda

Massive pre-trained language models have garnered attention and controversy due to their ability to generate human-like responses: attention due to their frequent indistinguishability from human-generated phraseology and narratives, and…

Physics Education · Physics 2023-05-23 Gerd Kortemeyer

Systems like ChatGPT and Claude assist billions through proactive dialogue-offering unsolicited, task-relevant information. Drawing on Cognitive Load Theory, we study how cognitive load shapes performance in AI-assisted knowledge work. We…

Artificial Intelligence · Computer Science 2026-03-10 Brandon Lepine , Juho Kim , Pamela Mishkin , Matthew Beane

We explore the evolving efficacy of three generative pre-trained transformer (GPT) models in generating answers for multiple-choice questions (MCQ) from introductory and intermediate Python programming courses in higher education. We focus…

Computers and Society · Computer Science 2023-11-17 Jaromir Savelka , Arav Agarwal , Christopher Bogart , Majd Sakr

Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by ablating a refusal direction from model activations, aiming…

Artificial Intelligence · Computer Science 2026-05-22 Giorgio Piras , Raffaele Mura , Fabio Brau , Maura Pintor , Luca Oneto , Fabio Roli , Battista Biggio

Recent advances in natural language processing and machine learning have led to the development of chatbot models, such as ChatGPT, that can engage in conversational dialogue with human users. However, the ability of these models to…

Cryptography and Security · Computer Science 2023-07-20 Bocheng Chen , Guangjing Wang , Hanqing Guo , Yuanda Wang , Qiben Yan

OpenAI's ChatGPT language model has gained popularity as a powerful tool for complex problem-solving and information retrieval. However, concerns arise about the reproduction of biases present in the language-specific training data. In this…

Computation and Language · Computer Science 2023-08-02 Daniel Kazenwadel , Christoph V. Steinert

While large language models (LLMs) such as ChatGPT and PaLM have demonstrated remarkable performance in various language understanding and generation tasks, their capabilities in complex reasoning and intricate knowledge utilization still…

Computation and Language · Computer Science 2023-10-11 Haodi Zhang , Min Cai , Xinhe Zhang , Chen Jason Zhang , Rui Mao , Kaishun Wu