paper-with-me

Papers

Exploring Human-LLM Conversations: Mental Models and the Originator of Toxicity

2024-07-08 · Johannes Schneider, Arianna Casanova Flores, Anne-Catherine Kranz

This study explores real-world human interactions with large language models (LLMs) in diverse, unconstrained settings in contrast to most prior research focusing on ethically trimmed models like ChatGPT for specific tasks. We aim to understand the originator of toxicity. Our findings show that although LLMs are rightfully accused of providing toxic content, it is mostly demanded or at least provoked by humans who actively seek such content. Our manual analysis of hundreds of conversations judged as toxic by APIs commercial vendors, also raises questions with respect to current practices of what user requests are refused to answer. Furthermore, we conjecture based on multiple empirical indicators that humans exhibit a change of their mental model, switching from the mindset of interacting with a machine more towards interacting with a human.

📄 PDF Abstract BibTeX arXiv:2407.05977

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation

2022-05-01 · Nitesh Goyal, Ian Kivlichan, Rachel Rosen, Lucy Vasserman

Machine learning models are commonly used to detect toxicity in online conversations. These models are trained on datasets annotated by human raters. We explore how raters' self-described identities impact how they annot…

Revisiting Contextual Toxicity Detection in Conversations

2021-11-24 · Atijit Anuchitanukul, Julia Ive, Lucia Specia

Understanding toxicity in user conversations is undoubtedly an important problem. Addressing "covert" or implicit cases of toxicity is particularly hard and requires context. Very few previous studies have analysed the i…

Data AugmentationToxic Comment Classification

Say ‘YES’ to Positivity: Detecting Toxic Language in Workplace Communications

2021-11-01 · Findings (EMNLP) 2021 11 · Meghana Moorthy Bhat, Saghar Hosseini, Ahmed Hassan Awadallah, Paul Bennett 외

Workplace communication (e.g. email, chat, etc.) is a central part of enterprise productivity. Healthy conversations are crucial for creating an inclusive environment and maintaining harmony in an organization. Toxic com…

Exploring the Impact of Personality Traits on LLM Bias and Toxicity

2025-02-18 · Shuo Wang, Renhao Li, Xi Chen, Yulin Yuan 외

With the different roles that AI is expected to play in human life, imbuing large language models (LLMs) with different personalities has attracted increasing research interests. While the "personification" enhances huma…

Text Generation

Toxicity Detection: Does Context Really Matter?

2020-06-01 · ACL 2020 6 · John Pavlopoulos, Jeffrey Sorensen, Lucas Dixon, Nithum Thain 외

Moderation is crucial to promoting healthy on-line discussions. Although several `toxicity' detection datasets and models have been published, most of them ignore the context of the posts, implicitly assuming that commen…