I Hackathon Somos NLP: PLN en Español

non-profit

https://somosnlp.org/hackathon

Activity Feed Request to join this org

AI & ML interests

Hackathon de PLN en español open-source y enfocado a los Objetivos de Desarrollo Sostenible de la ONU. Organizado por Somos NLP y patrocinado por Platzi, Paperspace y Hugging Face.

authored a paper about 1 month ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published Jul 2 • 77

submitted a paper to Daily Papers about 1 month ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published Jul 2 • 77

authored a paper 3 months ago

Models That Know How Evaluations Are Designed Score Safer

Paper • 2605.28591 • Published May 27 • 10

submitted a paper to Daily Papers 3 months ago

Models That Know How Evaluations Are Designed Score Safer

Paper • 2605.28591 • Published May 27 • 10

authored a paper 6 months ago

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves

Paper • 2602.24210 • Published May 29

authored 2 papers 6 months ago

BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data

Paper • 2510.10159 • Published Oct 11, 2025 • 3

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Paper • 2511.04703 • Published Nov 3, 2025 • 8

authored a paper 11 months ago

EmbeddingGemma: Powerful and Lightweight Text Representations

Paper • 2509.20354 • Published Sep 24, 2025 • 51

authored 4 papers 11 months ago

Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings

Paper • 2509.14405 • Published Sep 17, 2025 • 2

Psycholinguistic Word Features: a New Approach for the Evaluation of LLMs Alignment with Humans

Paper • 2506.22439 • Published May 29, 2025 • 3

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Paper • 2509.14233 • Published Sep 17, 2025 • 24

La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America

Paper • 2507.00999 • Published Jul 1, 2025 • 3

authored 2 papers about 1 year ago

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers

Paper • 2506.15674 • Published Jun 18, 2025 • 2

C-SEO Bench: Does Conversational SEO Work?

Paper • 2506.11097 • Published Jun 6, 2025 • 2

in somosnlp-hackathon-2022/spanish-to-quechua-translation about 1 year ago

not working

#1 opened about 1 year ago by

update sdk

#3 opened about 1 year ago by

update gradio

#2 opened about 1 year ago by

posted an update about 1 year ago

Post

412

📜 Accepted at ACL 2025! Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
We propose to fine-tune LLMs to generate diverse chains of thought (DCoT) in a single inference step. This enables within-inference refinement of the cots, no external feedback needed!
🔗 https://arxiv.org/abs/2407.03181

authored 2 papers about 1 year ago

Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation

Paper • 2504.07072 • Published Apr 9, 2025 • 9

It's the same but not the same: Do LLMs distinguish Spanish varieties?

Paper • 2504.20049 • Published Apr 8, 2025