SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.08795 · 2024

Coverage-based Fairness in Multi-document Summarization

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Fairness in multi-document summarization (MDS) measures whether a system can generate a summary fairly representing information from documents with different social attribute values. Fairness in MDS is crucial since a fair summary can offer readers a comprehensive view. Previous works focus on quantifying summary-level fairness using Proportional Representation, a fairness measure based on Statistical Parity. However, Proportional Representation does not consider redundancy in input documents and overlooks corpus-level unfairness. In this work, we propose a new summary-level fairness measure, Equal Coverage, which is based on coverage of documents with different social attribute values and considers the redundancy within documents. To detect the corpus-level unfairness, we propose a new corpus-level measure, Coverage Parity. Our human evaluations show that our measures align more with our definition of fairness. Using our measures, we evaluate the fairness of thirteen different LLMs. We find that Claude3-sonnet is the fairest among all evaluated LLMs. We also find that almost all LLMs overrepresent different social attribute values. The code is available at https://github.com/leehaoyuan/coverage_fairness.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2412.08795")
get_code_for_paper("2412.08795")
have("2412.08795")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2412.08795.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2412.08795.svg)](https://syntology.ai/paper/2412.08795)

Connect an agent — have() is free.