Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas
Role-play in large language models (LLMs) enhances their ability to generate contextually relevant and high-quality responses by simulating diverse cognitive perspectives. However, our study identifies significant risks associated with this technique. First, we demonstrate that autotuning, a method used to auto-select models' roles based on the question, can lead to the generation of harmful outputs, even when the model is tasked with adopting neutral roles. Second, we investigate how different roles affect the likelihood of generating biased or harmful content. Through testing on benchmarks containing stereotypical and harmful questions, we find that role-play consistently amplifies the risk of biased outputs. Our results underscore the need for careful consideration of both role simulation and tuning processes when deploying LLMs in sensitive or high-stakes contexts.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingLarge Language ModelSimilar Papers 제목 키워드 기반
Reasoning Does Not Necessarily Improve Role-Playing Ability
The application of role-playing large language models (LLMs) is rapidly expanding in both academic and commercial domains, driving an increasing demand for high-precision role-playing models. Simultaneously, the rapid ad…
EMNLP: Educator-role Moral and Normative Large Language Models Profiling
Simulating Professions (SP) enables Large Language Models (LLMs) to emulate professional roles. However, comprehensive psychological and ethical evaluation in these contexts remains lacking. This paper introduces EMNLP, …
The Rosetta Paradox: Domain-Specific Performance Inversions in Large Language Models
While large language models, such as GPT and BERT, have already demonstrated unprecedented skills in everything from natural language processing to domain-specific applications, there came an unexplored phenomenon we ter…
Common Sense ReasoningSpecificityThe Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs
Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high performance on in-distribution benchmarks while demonstrating brittle reaso…
Reinforcement LearningCan Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?
Multi-modal large language models (MLLMs) exhibit strong general-purpose capabilities, yet still struggle on Fine-Grained Visual Classification (FGVC), a core perception task that requires subtle visual discrimination an…