ALEE generates AMR-based English minimal pairs with fine-grained semantic shifts, translates them, and evaluates embedding models on 275+ languages to expose cross-lingual gaps linked to training data and tokenization.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , month=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CL 5years
2026 5representative citing papers
OpenBibleTTS supplies speech data and alignments for 37 underrepresented languages and shows that no single TTS system leads on all metrics, with Gemini-TTS highest in listener ratings but monolingual EveryVoice models strongest on intelligibility for several African languages.
Activation steering on early layers improves diversity of synthetic data for low-resource languages and often boosts downstream classifier performance compared to non-steered prompting.
Explicit purpose instructions improve LLM translation adaptedness across 50 languages and 8 domains, with larger gains on informal text, while standard metrics often penalize the adapted outputs.
Large-scale benchmarks of multilingual embeddings and QE models show no universal performer; direction-aware routing and calibration recommended for parallel data assessment.
citing papers explorer
-
ALEE: Any-Language Evaluation of Embeddings via English-Centric Minimal Pairs
ALEE generates AMR-based English minimal pairs with fine-grained semantic shifts, translates them, and evaluates embedding models on 275+ languages to expose cross-lingual gaps linked to training data and tokenization.
-
OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages
OpenBibleTTS supplies speech data and alignments for 37 underrepresented languages and shows that no single TTS system leads on all metrics, with Gemini-TTS highest in listener ratings but monolingual EveryVoice models strongest on intelligibility for several African languages.
-
Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation
Activation steering on early layers improves diversity of synthetic data for low-resource languages and often boosts downstream classifier performance compared to non-steered prompting.
-
Beyond "To whom it may concern": Tailoring Machine Translation to Audience and Intent
Explicit purpose instructions improve LLM translation adaptedness across 50 languages and 8 domains, with larger gains on informal text, while standard metrics often penalize the adapted outputs.
-
Model-Based Quality Assessment for Massively Multilingual Parallel Data
Large-scale benchmarks of multilingual embeddings and QE models show no universal performer; direction-aware routing and calibration recommended for parallel data assessment.