paper-with-me

홈 › Papers

An Evaluation of LLMs for Detecting Harmful Computing Terms

2025-03-12 · Joshua Jacas, Hana Winchester, Alicia Boyd, Brittany Johnson

Detecting harmful and non-inclusive terminology in technical contexts is critical for fostering inclusive environments in computing. This study explores the impact of model architecture on harmful language detection by evaluating a curated database of technical terms, each paired with specific use cases. We tested a range of encoder, decoder, and encoder-decoder language models, including BERT-base-uncased, RoBERTa large-mnli, Gemini Flash 1.5 and 2.0, GPT-4, Claude AI Sonnet 3.5, T5-large, and BART-large-mnli. Each model was presented with a standardized prompt to identify harmful and non-inclusive language across 64 terms. Results reveal that decoder models, particularly Gemini Flash 2.0 and Claude AI, excel in nuanced contextual analysis, while encoder models like BERT exhibit strong pattern recognition but struggle with classification certainty. We discuss the implications of these findings for improving automated detection tools and highlight model-specific strengths and limitations in fostering inclusive communication in technical domains.

📄 PDF Abstract BibTeX arXiv:2503.09341

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors

2025-05-20 · Maheep Chaudhary, Fazl Barez

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predi…

Towards Comprehensive Detection of Chinese Harmful Memes

2024-10-03 · Junyu Lu, Bo Xu, Xiaokun Zhang, Hongbo Wang 외

This paper has been accepted in the NeurIPS 2024 D & B Track. Harmful memes have proliferated on the Chinese Internet, while research on detecting Chinese harmful memes significantly lags behind due to the absence of rel…

A Chinese Dataset for Evaluating the Safeguards in Large Language Models

2024-02-19 · Yuxia Wang, Zenan Zhai, Haonan Li, Xudong Han 외

Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the ri…

Sound Probabilistic Safety Bounds for Large Language Models

2026-07-22 · Mahdi Nazeri, Anne-Kathrin Schmuck, Sadegh Soudjani, Alessandro Abate arxiv

We propose a novel framework for computing rigorous bounds on the probability that a large language model (LLM) generates harmful output to a given prompt. We study a new application of the Clopper-Pearson confidence int…

SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models

2026-05-12 · Xinyi Zeng, Xue Yang, Jingyuan Zhang, Huanqian Yan 외 arxiv

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely o…