EuroBERT: Scaling Multilingual Encoders for European Languages Paper • 2503.05500 • Published 10 days ago • 72
SynthDetoxM Collection Data and models from NAACL 2025 paper "SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators" by Moskovskiy et al. • 4 items • Updated 11 days ago • 2
When an LLM is apprehensive about its answers -- and when its uncertainty is justified Paper • 2503.01688 • Published 14 days ago • 19
GHOST 2.0: generative high-fidelity one shot transfer of heads Paper • 2502.18417 • Published 20 days ago • 63
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers Paper • 2502.15007 • Published 24 days ago • 163
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? Paper • 2502.14502 • Published 25 days ago • 85
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity Paper • 2502.13063 • Published 27 days ago • 67
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators Paper • 2502.06394 • Published Feb 10 • 86
The Differences Between Direct Alignment Algorithms are a Blur Paper • 2502.01237 • Published Feb 3 • 112
Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification Paper • 2311.13937 • Published Nov 23, 2023 • 1
Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management Paper • 2406.19543 • Published Jun 27, 2024 • 1
Multilingual and Explainable Text Detoxification with Parallel Corpora Paper • 2412.11691 • Published Dec 16, 2024 • 1
view article Article Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference Jan 16 • 71
LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models Paper • 2501.00874 • Published Jan 1 • 13
Facilitating large language model Russian adaptation with Learned Embedding Propagation Paper • 2412.21140 • Published Dec 30, 2024 • 18