Summary of Coverage-based Fairness in Multi-document Summarization, by Haoyuan Li et al.
Coverage-based Fairness in Multi-document Summarization
by Haoyuan Li, Yusen Zhang, Rui Zhang, Snigdha Chaturvedi
First submitted to arxiv on: 11 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 This research paper proposes two new measures to quantify fairness in multi-document summarization (MDS). The first measure, Equal Coverage, assesses summary-level fairness by considering the coverage of documents with different social attributes and redundancy within documents. The second measure, Coverage Parity, detects corpus-level unfairness. The authors evaluate the fairness of 13 language models using these measures and find that Claude3-sonnet is the fairest model, while most models overrepresent different social attribute values. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make sure that summaries from different sources are fair and accurate. Right now, there’s no good way to measure this kind of fairness. The researchers propose two new methods: Equal Coverage and Coverage Parity. They test these measures on 13 language models and find that one model is much better than the others at being fair. Most models tend to emphasize certain viewpoints over others. |
Keywords
» Artificial intelligence » Summarization
