"Cold, Calculated, and Condescending": How AI Identifies and Explains Ableism Compared to Disabled People
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912404441399296 |
|---|---|
| author | Phutane, Mahika Seelam, Ananya Vashistha, Aditya |
| author_facet | Phutane, Mahika Seelam, Ananya Vashistha, Aditya |
| contents | People with disabilities (PwD) regularly encounter ableist hate and microaggressions online. These spaces are generally moderated by machine learning models, but little is known about how effectively AI models identify ableist speech and how well their judgments align with PwD. To investigate this, we curated a first-of-its-kind dataset of 200 social media comments targeted towards PwD, and prompted state-of-the art AI models (i.e., Toxicity Classifiers, LLMs) to score toxicity and ableism for each comment, and explain their reasoning. Then, we recruited 190 participants to similarly rate and explain the harm, and evaluate LLM explanations. Our mixed-methods analysis highlighted a major disconnect: AI underestimated toxicity compared to PwD ratings, while its ableism assessments were sporadic and varied. Although LLMs identified some biases, its explanations were flawed--they lacked nuance, made incorrect assumptions, and appeared judgmental instead of educational. Going forward, we discuss challenges and opportunities in designing moderation systems for ableism, and advocate for the involvement of intersectional disabled perspectives in AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03448 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | "Cold, Calculated, and Condescending": How AI Identifies and Explains Ableism Compared to Disabled People Phutane, Mahika Seelam, Ananya Vashistha, Aditya Human-Computer Interaction Artificial Intelligence People with disabilities (PwD) regularly encounter ableist hate and microaggressions online. These spaces are generally moderated by machine learning models, but little is known about how effectively AI models identify ableist speech and how well their judgments align with PwD. To investigate this, we curated a first-of-its-kind dataset of 200 social media comments targeted towards PwD, and prompted state-of-the art AI models (i.e., Toxicity Classifiers, LLMs) to score toxicity and ableism for each comment, and explain their reasoning. Then, we recruited 190 participants to similarly rate and explain the harm, and evaluate LLM explanations. Our mixed-methods analysis highlighted a major disconnect: AI underestimated toxicity compared to PwD ratings, while its ableism assessments were sporadic and varied. Although LLMs identified some biases, its explanations were flawed--they lacked nuance, made incorrect assumptions, and appeared judgmental instead of educational. Going forward, we discuss challenges and opportunities in designing moderation systems for ableism, and advocate for the involvement of intersectional disabled perspectives in AI. |
| title | "Cold, Calculated, and Condescending": How AI Identifies and Explains Ableism Compared to Disabled People |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2410.03448 |