Intentional Biases in LLM Responses
In this study we intentionally introduce biases into large language model responses in an attempt to create specific personas for interactive media purposes. We explore the differences between open source models such as Falcon-7b and the GPT-4 model from Open AI, and we quantify some differences in responses afforded by the two systems. We find that the guardrails in the GPT-4 mixture of experts models with a supervisor, while useful in assuring AI alignment in general, are detrimental in trying to construct personas with a variety of uncommon viewpoints. This study aims to set the groundwork for future exploration in intentional biases of large language models such that these practices can be applied in the creative field, and new forms of media.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingLarge Language ModelMixture-of-ExpertsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Stereotype or Personalization? User Identity Biases Chatbot Recommendations
We demonstrate that when people use large language models (LLMs) to generate recommendations, the LLMs produce responses that reflect both what the user wants and who the user is. While personalized recommendations are o…
ChatbotLeveraging Self-Supervised Training for Unintentional Action Recognition
Unintentional actions are rare occurrences that are difficult to define precisely and that are highly dependent on the temporal context of the action. In this work, we explore such actions and seek to identify the points…
Action RecognitionVisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
This research investigates both explicit and implicit social biases exhibited by Vision-Language Models (VLMs). The key distinction between these bias types lies in the level of awareness: explicit bias refers to conscio…
Image DescriptionMultiple-choiceSelf-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models
Fair decisions require ignoring irrelevant, potentially biasing, information. To achieve this, decision-makers need to approximate what decision they would have made had they not known certain facts, such as the gender o…
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences. Although these methods are designed to teach a model to generate preferred responses more f…