Silver-Tongued and Sundry: Exploring Intersectional Pronouns with ChatGPT
- URL: http://arxiv.org/abs/2405.08238v1
- Date: Mon, 13 May 2024 23:38:50 GMT
- Title: Silver-Tongued and Sundry: Exploring Intersectional Pronouns with ChatGPT
- Authors: Takao Fujii, Katie Seaborn, Madeleine Steeds,
- Abstract summary: We studied the case of identity simulation through Japanese first-person pronouns.
Pronouns evoke perceptions of social identities in ChatGPT at the intersections of gender, age, region, and formality.
This work highlights the importance of pronoun use for social identity simulation, provides a language-based methodology for culturally-sensitive persona development, and advances the potential of intersectional identities in intelligent agents.
- Score: 25.5053022752019
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: ChatGPT is a conversational agent built on a large language model. Trained on a significant portion of human output, ChatGPT can mimic people to a degree. As such, we need to consider what social identities ChatGPT simulates (or can be designed to simulate). In this study, we explored the case of identity simulation through Japanese first-person pronouns, which are tightly connected to social identities in intersectional ways, i.e., intersectional pronouns. We conducted a controlled online experiment where people from two regions in Japan (Kanto and Kinki) witnessed interactions with ChatGPT using ten sets of first-person pronouns. We discovered that pronouns alone can evoke perceptions of social identities in ChatGPT at the intersections of gender, age, region, and formality, with caveats. This work highlights the importance of pronoun use for social identity simulation, provides a language-based methodology for culturally-sensitive persona development, and advances the potential of intersectional identities in intelligent agents.
Related papers
- Are Generative Language Models Multicultural? A Study on Hausa Culture and Emotions using ChatGPT [4.798444680860121]
We compare responses generated by ChatGPT with those provided by native Hausa speakers on 37 culturally relevant questions.
Our results show that ChatGPT has some level of similarity to human responses, but also exhibits some gaps and biases in its knowledge and awareness of the Hausa culture and emotions.
arXiv Detail & Related papers (2024-06-27T19:42:13Z) - CharacterGLM: Customizing Chinese Conversational AI Characters with
Large Language Models [66.4382820107453]
We present CharacterGLM, a series of models built upon ChatGLM, with model sizes ranging from 6B to 66B parameters.
Our CharacterGLM is designed for generating Character-based Dialogues (CharacterDial), which aims to equip a conversational AI system with character customization for satisfying people's inherent social desires and emotional needs.
arXiv Detail & Related papers (2023-11-28T14:49:23Z) - Fictional Worlds, Real Connections: Developing Community Storytelling
Social Chatbots through LLMs [11.81497469617973]
We introduce Social Storytellings (SSCs) to transform fictional game characters into "live" social entities within player communities.
Our story engineering process includes three steps: Character and story creation, defining the SC's personality and worldview, and presenting live stories to the community.
Our mixed-method analysis, based on questionnaires and interviews with community members, reveals that storytelling significantly enhances the engagement and believability of SCs in community settings.
arXiv Detail & Related papers (2023-09-20T17:23:05Z) - "I'm fully who I am": Towards Centering Transgender and Non-Binary
Voices to Measure Biases in Open Language Generation [69.25368160338043]
Transgender and non-binary (TGNB) individuals disproportionately experience discrimination and exclusion from daily life.
We assess how the social reality surrounding experienced marginalization of TGNB persons contributes to and persists within Open Language Generation.
We introduce TANGO, a dataset of template-based real-world text curated from a TGNB-oriented community.
arXiv Detail & Related papers (2023-05-17T04:21:45Z) - Training Conversational Agents with Generative Conversational Networks [74.9941330874663]
We use Generative Conversational Networks to automatically generate data and train social conversational agents.
We evaluate our approach on TopicalChat with automatic metrics and human evaluators, showing that with 10% of seed data it performs close to the baseline that uses 100% of the data.
arXiv Detail & Related papers (2021-10-15T21:46:39Z) - SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement
Learning Agents [23.719833581321033]
Building embodied autonomous agents capable of participating in social interactions with humans is one of the main challenges in AI.
We argue that aiming towards human-level AI requires a broader set of key social skills.
We present SocialAI, a benchmark to assess the acquisition of social skills of DRL agents.
arXiv Detail & Related papers (2021-07-02T10:39:18Z) - LGBTQ-AI? Exploring Expressions of Gender and Sexual Orientation in
Chatbots [4.511923587827302]
We conducted semi-structured interviews with 5 text-based conversational agents to explore this topic.
We identified 6 common themes around the expression of gender and sexual identity.
It is evident that chatbots differ from human dialogue partners as they lack the flexibility understanding enabled by human experience.
arXiv Detail & Related papers (2021-06-03T18:47:52Z) - Towards Socially Intelligent Agents with Mental State Transition and
Human Utility [97.01430011496576]
We propose to incorporate a mental state and utility model into dialogue agents.
The hybrid mental state extracts information from both the dialogue and event observations.
The utility model is a ranking model that learns human preferences from a crowd-sourced social commonsense dataset.
arXiv Detail & Related papers (2021-03-12T00:06:51Z) - Can You be More Social? Injecting Politeness and Positivity into
Task-Oriented Conversational Agents [60.27066549589362]
Social language used by human agents is associated with greater users' responsiveness and task completion.
The model uses a sequence-to-sequence deep learning architecture, extended with a social language understanding element.
Evaluation in terms of content preservation and social language level using both human judgment and automatic linguistic measures shows that the model can generate responses that enable agents to address users' issues in a more socially appropriate way.
arXiv Detail & Related papers (2020-12-29T08:22:48Z) - Listener's Social Identity Matters in Personalised Response Generation [19.35779310590447]
We investigate how the listener's identity influences the language used in Chinese dialogues on social media.
The experiment results demonstrate that the listener's identity indeed matters in the language use of responses.
By additionally modelling the listener's identity, the personalised response generator performs better in its own identity.
arXiv Detail & Related papers (2020-10-27T14:57:21Z) - I love your chain mail! Making knights smile in a fantasy game world:
Open-domain goal-oriented dialogue agents [69.68400056148336]
We train a goal-oriented model with reinforcement learning against an imitation-learned chit-chat'' model.
We show that both models outperform an inverse model baseline and can converse naturally with their dialogue partner in order to achieve goals.
arXiv Detail & Related papers (2020-02-07T16:22:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.