PingPong: Hand-Curated Code-Switched Multi-Party Conversation Benchmark Accepted at EMNLP 2026

ponguru · x · 2026-09-14

The SARAL team's 'PingPong' paper is accepted at EMNLP 2026: a rare manually curated benchmark for realistic code-switched multi-party conversations, spanning 6 language combinations and 3 tasks. Evaluation shows current models still struggle with natural code-switching. Paper, data, and a Hindi podcast walkthrough are public.

Related event: PingPong: Handcrafted Code-Switching Dialogue Benchmark Accepted by EMNLP 2026(2 posts)→

Original post →

More from Models

Models channel →