Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909023746392064 |
|---|---|
| author | Ashkinaze, Joshua Guan, Ruijia Kurek, Laura Adar, Eytan Budak, Ceren Gilbert, Eric |
| author_facet | Ashkinaze, Joshua Guan, Ruijia Kurek, Laura Adar, Eytan Budak, Ceren Gilbert, Eric |
| contents | Large language models (LLMs) are trained on broad corpora and then used in communities with specialized norms. Is providing LLMs with community rules enough for models to follow these norms? We evaluate LLMs' capacity to detect (Task 1) and correct (Task 2) biased Wikipedia edits according to Wikipedia's Neutral Point of View (NPOV) policy. LLMs struggled with bias detection, achieving only 64% accuracy on a balanced dataset. Models exhibited contrasting biases (some under- and others over-predicted bias), suggesting distinct priors about neutrality. LLMs performed better at generation, removing 79% of words removed by Wikipedia editors. However, LLMs made additional changes beyond Wikipedia editors' simpler neutralizations, resulting in high-recall but low-precision editing. Interestingly, crowdworkers rated AI rewrites as more neutral (70%) and fluent (61%) than Wikipedia-editor rewrites. Qualitative analysis found LLMs sometimes applied NPOV more comprehensively than Wikipedia editors but often made extraneous non-NPOV-related changes (such as grammar). LLMs may apply rules in ways that resonate with the public but diverge from community experts. While potentially effective for generation, LLMs may reduce editor agency and increase moderation workload (e.g., verifying additions). Even when rules are easy to articulate, having LLMs apply them like community members may still be difficult. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04183 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms Ashkinaze, Joshua Guan, Ruijia Kurek, Laura Adar, Eytan Budak, Ceren Gilbert, Eric Computation and Language Artificial Intelligence Computers and Society Human-Computer Interaction Large language models (LLMs) are trained on broad corpora and then used in communities with specialized norms. Is providing LLMs with community rules enough for models to follow these norms? We evaluate LLMs' capacity to detect (Task 1) and correct (Task 2) biased Wikipedia edits according to Wikipedia's Neutral Point of View (NPOV) policy. LLMs struggled with bias detection, achieving only 64% accuracy on a balanced dataset. Models exhibited contrasting biases (some under- and others over-predicted bias), suggesting distinct priors about neutrality. LLMs performed better at generation, removing 79% of words removed by Wikipedia editors. However, LLMs made additional changes beyond Wikipedia editors' simpler neutralizations, resulting in high-recall but low-precision editing. Interestingly, crowdworkers rated AI rewrites as more neutral (70%) and fluent (61%) than Wikipedia-editor rewrites. Qualitative analysis found LLMs sometimes applied NPOV more comprehensively than Wikipedia editors but often made extraneous non-NPOV-related changes (such as grammar). LLMs may apply rules in ways that resonate with the public but diverge from community experts. While potentially effective for generation, LLMs may reduce editor agency and increase moderation workload (e.g., verifying additions). Even when rules are easy to articulate, having LLMs apply them like community members may still be difficult. |
| title | Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms |
| topic | Computation and Language Artificial Intelligence Computers and Society Human-Computer Interaction |
| url | https://arxiv.org/abs/2407.04183 |