Introduces the MEA benchmark for multi-target cross-lingual summarization across 24 languages and demonstrates that activation steering from English summarization representations improves performance.
Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3representative citing papers
GRPO reinforcement learning on the new PolyFact dataset outperforms SFT and CPT for cross-lingual factual consistency in Qwen-2.5-7B and OLMo-2-7B by reducing language specialization in MLP and attention layers.
citing papers explorer
-
Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization
Introduces the MEA benchmark for multi-target cross-lingual summarization across 24 languages and demonstrates that activation steering from English summarization representations improves performance.
-
Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning
GRPO reinforcement learning on the new PolyFact dataset outperforms SFT and CPT for cross-lingual factual consistency in Qwen-2.5-7B and OLMo-2-7B by reducing language specialization in MLP and attention layers.
- Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining