$MLING multilingual

Latest papers

1. Babbar26 main x genre cs.IR · 19 Oct · 1 hit

   We introduce Babbar26, a multilingual dataset of 1111 web pages from 1006 domains in five languages (English, French, German, Spanish,…

2. DeepSEA: A Multilingual Evaluation Benchmark for Southeast Asia cs.CL · 19 Oct · 2 hits

   …fertility analysis. We hope these findings shed light on the development of next-generation inclusive multilingual models.

3. Multilingual Voicemail and Answering Machine Detection via Pretrained Audio Embeddings and Gradient Boosting Machines cs.SD · 19 Oct · 1 hit

   Answering machine detection (AMD) is a fundamental task in telephony that classifies whether an answered call…

4. Financial Literacy and the Functional Shape of Subjective Time Deformation in Intertemporal Choice stat.AP · 19 Oct · 1 hit

   …reconstructed subjective time as a functional rather than scalar outcome. Data were collected through a multilingual online questionnaire administered to a convenience and snowball sample of 140 adults, who…

5. Scaling Synthetic Pre-training Data and Evaluation for Indic LLMs cs.CL · 19 Oct · 3 hits

   Building capable language models for India requires scalable multilingual data and robust evaluation. We introduce Nemotron-Pretraining-Indic-v1, a synthetic pretraining…

6. Arabic Financial NLP cs.CL · 19 Oct · 1 hit

   …and Arabic text processing to the analysis of vocabulary, evaluation, entities, causal attribution and multilingual reporting. It then examines what financial summaries and retrieval-grounded answers preserve or…

7. Diffusion Language Models Change Speed Across Tasks and Languages cs.CL · 19 Oct · 1 hit

   …final answer is cheap when it repeats the model's reasoning trace and costly when it adds something new. In multilingual generation, we find that highly tokenized languages also require more passes per token, adding…

8. Editing as Language: Teaching LLM Agents a Grammar for Native Context Editing cs.AI · 18 Oct · 1 hit

   …workflows. On four long-horizon agentic benchmarks (Terminal-Bench 2.0, SWE-bench Verified, SWE-bench Multilingual, and SWE-bench Pro), NCE improves the average task success rate over the base model by 5.6…