Two NLP papers accepted to EMNLP 2026: Cross-lingual alignment and bias evaluation

Bollegala · x · 2026-08-21

Two papers were accepted to EMNLP 2026. The main conference paper proposes cross-lingual representation alignment via token-level optimal transport in a language-agnostic space. The Findings paper introduces DyMT-ESB for dynamically evaluating social bias in multi-turn user-LLM interactions.

Related event: Two NLP Papers on Multilingual Alignment and Bias Accepted to EMNLP 2026(2 posts)→

Original post →

More from Research

Research channel →