SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration
The potential social harms that large language models pose, such as generating offensive content and reinforcing biases, are steeply rising. Existing works focus on coping with this concern while interacting with ill-intentioned users, such as those who explicitly make hate speech or elicit harmful responses. However, discussions on sensitive issues can become toxic even if the users are well-intentioned. For safer models in such scenarios, we present the Sensitive Questions and Acceptable Response (SQuARe) dataset, a large-scale Korean dataset of 49k sensitive questions with 42k acceptable and 46k non-acceptable responses. The dataset was constructed leveraging HyperCLOVA in a human-in-the-loop manner based on real news headlines. Experiments show that acceptable response generation significantly improves for HyperCLOVA and GPT-3, demonstrating the efficacy of this dataset.
Code (1)
Tasks
Response GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation
Cultural biases in multilingual datasets pose significant challenges for their effectiveness as global benchmarks. These biases stem not only from language but also from the cultural knowledge required to interpret quest…
MMLUTextSquare: Scaling up Text-Centric Visual Instruction Tuning
Text-centric visual question answering (VQA) has made great strides with the development of Multimodal Large Language Models (MLLMs), yet open-source models still fall short of leading models like GPT4V and Gemini, partl…
HallucinationHallucination EvaluationQuestion AnsweringVisual Question Answering+1Time-Sensitive Recommendation From Recurrent User Activities
By making personalized suggestions, a recommender system is playing a crucial role in improving the engagement of users in modern web-services. However, most recommendation algorithms do not explicitly take into account …
Point ProcessesRecommendation SystemsAccelerated Gradient Temporal Difference Learning
The family of temporal difference (TD) methods span a spectrum from computationally frugal linear methods like TD({\lambda}) to data efficient least squares methods. Least square methods make the best use of available da…
Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maxims
Large language models (LLMs) are being increasingly used to answer subjective, information-seeking questions, where users are sensitive to how responses are communicated, not just whether the answers are correct. Existin…