Not Lost After All: How Cross-Encoder Attribution Challenges Position Bias Assumptions in LLM Summarization | EMNLP 2025

Jan 1, 2025ยท
Abeer Badawi
Abeer Badawi
,
Elahe Rahimi
,
Hassan Sajjad
,
Domenic Rosati
,
Elham Dolatabadi
,
Frank Rudzicz
ยท 1 min read
URL
Type
Publication
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing

Institutions:

  1. Dalhousie University, Canada
  2. Vector Institute, Canada
  3. York University, Canada
Abeer Badawi
Authors
Abeer Badawi
Postdoctoral and Faculty Affiliate Researcher