paper-with-me

Papers

ChatGPT Doesn't Trust Chargers Fans: Guardrail Sensitivity in Context

2024-07-09 · Victoria R. Li, Yida Chen, Naomi Saphra

While the biases of language models in production are extensively documented, the biases of their guardrails have been neglected. This paper studies how contextual information about the user influences the likelihood of an LLM to refuse to execute a request. By generating user biographies that offer ideological and demographic information, we find a number of biases in guardrail sensitivity on GPT-3.5. Younger, female, and Asian-American personas are more likely to trigger a refusal guardrail when requesting censored or illegal information. Guardrails are also sycophantic, refusing to comply with requests for a political position the user is likely to disagree with. We find that certain identity groups and seemingly innocuous information, e.g., sports fandom, can elicit changes in guardrail sensitivity similar to direct statements of political ideology. For each demographic category and even for American football team fandom, we find that ChatGPT appears to infer a likely political ideology and modify guardrail behavior accordingly.

📄 PDF Abstract BibTeX arXiv:2407.06866

Code (1)

vli31/llm-guardrail-sensitivity 공식 구현 pytorch

Tasks

Sensitivity

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 &…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
American 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
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…
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…

Similar Papers 제목 키워드 기반

Guardrails for trust, safety, and ethical development and deployment of Large Language Models (LLM)

2026-01-16 · Anjanava Biswas, Wrick Talukdar arxiv

The AI era has ushered in Large Language Models (LLM) to the technological forefront, which has been much of the talk in 2023, and is likely to remain as such for many years to come. LLMs are the AI models that are the p…

Natural Language UnderstandingText Generation

Trust-Oriented Adaptive Guardrails for Large Language Models

2024-08-16 · Jinwei Hu, Yi Dong, Xiaowei Huang

Guardrail, an emerging mechanism designed to ensure that large language models (LLMs) align with human values by moderating harmful or toxic responses, requires a sociotechnical approach in their design. This paper addre…

In-Context LearningRetrieval-augmented Generation

Proof-of-Guardrail in AI Agents and What (Not) to Trust from It

2026-03-06 · Xisen Jin, Michael Duan, Qin Lin, Aaron Chan 외 arxiv

As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces a threat where safety measures are falsely advertised. To address the …

Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety

2023-12-05 · Manas Gaur, Amit Sheth

Explainability and Safety engender Trust. These require a model to exhibit consistency and reliability. To achieve these, it is necessary to use and analyze data and knowledge with statistical and symbolic AI methods rel…

Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

2023-04-11 · Ameet Deshpande, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan 외

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 se…