Summary of Seeing Like An Ai: How Llms Apply (and Misapply) Wikipedia Neutrality Norms, by Joshua Ashkinaze et al.
Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms
by Joshua Ashkinaze, Ruijia Guan, Laura Kurek, Eytan Adar, Ceren Budak, Eric Gilbert
First submitted to arxiv on: 4 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Large language models struggle to detect biased Wikipedia edits, achieving only 64% accuracy. While they can generate rewritten text that is more neutral and fluent than Wikipedia editors’, they often make extraneous changes that deviate from the original NPOV policy. This study shows that even with clear rules, LLMs may not fully replicate community norms. The models’ contrasting biases suggest distinct priors about neutrality, highlighting the importance of understanding their decision-making processes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large language models are trying to help with Wikipedia edits. They can do some things well, like making text more neutral and fluent. But they also make mistakes, like adding extra changes that aren’t needed. This study found that LLMs might be good at following rules, but not always in the same way as people who work on Wikipedia. It’s important to understand how these models think and decide what to do. |
