Persona-driven workflow and interface improve automated and human-AI red-teaming of generative AI by incorporating diverse perspectives into adversarial prompt creation.
& Ganguli, D
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
roles
background 4representative citing papers
Prompt-conditioned LLMs face irreducible error floors from language's limited information capacity and alignment constraints, proven via PAC-Bayes bounds on bilevel cheap-talk games for certain task families.
Freelancers use generative AI to support exploratory skill acquisition but not as their main resource due to reliability issues, leading to a shift toward survival-oriented upskilling and the emergence of invisible competencies that lack market validation.
CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.
RLHF-aligned language models show increasing resistance to red teaming with scale up to 52B parameters, unlike prompted or rejection-sampled models, supported by a released dataset of 38,961 attacks.
MRKL is a modular neuro-symbolic architecture that integrates LLMs with external knowledge and discrete reasoning to overcome limitations of pure neural language models.
The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job loss and environmental costs.
VLA benchmark success rates cannot distinguish semantic generalization from physical reasoning due to an identifiability gap in current evaluation protocols.
citing papers explorer
-
PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI
Persona-driven workflow and interface improve automated and human-AI red-teaming of generative AI by incorporating diverse perspectives into adversarial prompt creation.
-
On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners
Prompt-conditioned LLMs face irreducible error floors from language's limited information capacity and alignment constraints, proven via PAC-Bayes bounds on bilevel cheap-talk games for certain task families.
-
Upskilling with Generative AI: Practices and Challenges for Freelance Knowledge Workers
Freelancers use generative AI to support exploratory skill acquisition but not as their main resource due to reliability issues, leading to a shift toward survival-oriented upskilling and the emergence of invisible competencies that lack market validation.
-
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.
-
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
RLHF-aligned language models show increasing resistance to red teaming with scale up to 52B parameters, unlike prompted or rejection-sampled models, supported by a released dataset of 38,961 attacks.
-
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
MRKL is a modular neuro-symbolic architecture that integrates LLMs with external knowledge and discrete reasoning to overcome limitations of pure neural language models.
-
Ethical and social risks of harm from Language Models
The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job loss and environmental costs.
-
Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning
VLA benchmark success rates cannot distinguish semantic generalization from physical reasoning due to an identifiability gap in current evaluation protocols.