Auto-interpretation labels for SAE features generalize poorly across languages and scripts, missing the same semantic content up to 4x more often in Serbian than English and more in Cyrillic than Latin despite deterministic transliteration.
arXiv preprint arXiv:2404.11553 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A new pre-training task that maps languages bidirectionally in embedding space improves machine translation by up to 11.9 BLEU, cross-lingual QA by 6.72 BERTScore points, and understanding accuracy by over 5% over strong baselines.
Replacing tokens, freezing the corresponding embeddings, and tuning the rest of the model improves NLU performance on low-resource languages compared to full fine-tuning.
citing papers explorer
-
How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings
Auto-interpretation labels for SAE features generalize poorly across languages and scripts, missing the same semantic content up to 4x more often in Serbian than English and more in Cyrillic than Latin despite deterministic transliteration.
-
Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance
A new pre-training task that maps languages bidirectionally in embedding space improves machine translation by up to 11.9 BLEU, cross-lingual QA by 6.72 BERTScore points, and understanding accuracy by over 5% over strong baselines.
-
Modular Monolingual Adaptation using Pretrained Language Models
Replacing tokens, freezing the corresponding embeddings, and tuning the rest of the model improves NLU performance on low-resource languages compared to full fine-tuning.