MultiHashFormer enables hash-based autoregression in LMs by encoding tokens as multi-hash signatures, outperforming standard Transformers at 100M-3B scales while keeping parameter count constant for multilingual expansion.
hub
Fineweb2: One pipeline to scale them all -- adapting pre-training data processing to every language
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
LangMAP adapts UnigramLM for multilingual use to deliver language-specific tokenization from a shared vocabulary, boosting boundary alignment metrics across natural and programming languages with mixed downstream fine-tuning gains.
Grouped Query Experts applies per-group MoE routing to query heads in GQA, matching baseline accuracy while activating half the query heads on 250M models trained for 30B tokens.
PARAMΔ upcycles dense models to MoE for per-language experts and grafts post-training deltas to enable data-efficient language expansion while preserving original capabilities.
SARA aligns internal routing distributions in MoE layers to high-resource semantic anchors via symmetric JS divergence, improving low-resource language performance by 0.8-1.2% over standard instruction tuning on Global-MMLU.
LINK improves cross-lingual knowledge transfer via lexical substitutions in English pretraining data, yielding notable downstream gains and up to 2x training speedup across eight languages and five model sizes.
SomaliWeb v1 delivers a cleaned Somali corpus, efficient BPE tokenizer, and side-by-side language identification benchmark while documenting defects in prior multilingual datasets.
Mixing auxiliary high-resource language data outperforms hyperparameter tuning in data-constrained bilingual pre-training, with gains equivalent to 2-13 times more unique target data.
Empirical study shows mixture pretraining tolerates higher target data repetition than single-source training, with a new repetition-aware scaling law enabling principled mixture selection based on data size, compute, and model scale.
Continued pretraining of ModernBERT on curated Portuguese data produces moBERTo, which reports top results on Portuguese retrieval reranking and PLUE-PT benchmarks.
Ishigaki-IDS is a verifier-aware LLM for generating validator-passing IDS files in BIM, reaching IDSAuditPass scores of 0.651-0.753 on a 166-case benchmark and cutting practitioner work time by 54.7%.
Mimir is a 1.6B multilingual concept model pretrained on 38.9 billion sentences across 46 languages and instruction-tuned on 66.8 million sentences across 35 languages, then compared to a token-based LM of similar size.
Granite Embedding Multilingual R2 releases 311M and 97M parameter bi-encoder models that achieve state-of-the-art retrieval performance on multilingual text, code, long-document, and reasoning datasets.
GLM-4.5, a 355B-parameter MoE model with hybrid reasoning, scores 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified while ranking 3rd overall and 2nd on agentic benchmarks.
citing papers explorer
-
MultiHashFormer: Hash-based Generative Language Models
MultiHashFormer enables hash-based autoregression in LMs by encoding tokens as multi-hash signatures, outperforming standard Transformers at 100M-3B scales while keeping parameter count constant for multilingual expansion.
-
LangMAP: A Language-Adaptive Approach to Tokenization
LangMAP adapts UnigramLM for multilingual use to deliver language-specific tokenization from a shared vocabulary, boosting boundary alignment metrics across natural and programming languages with mixed downstream fine-tuning gains.
-
Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention
Grouped Query Experts applies per-group MoE routing to query heads in GQA, matching baseline accuracy while activating half the query heads on 250M models trained for 30B tokens.
-
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE
PARAMΔ upcycles dense models to MoE for per-language experts and grafts post-training deltas to enable data-efficient language expansion while preserving original capabilities.
-
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
SARA aligns internal routing distributions in MoE layers to high-resource semantic anchors via symmetric JS divergence, improving low-resource language performance by 0.8-1.2% over standard instruction tuning on Global-MMLU.
-
Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions
LINK improves cross-lingual knowledge transfer via lexical substitutions in English pretraining data, yielding notable downstream gains and up to 2x training speedup across eight languages and five model sizes.
-
SomaliWeb v1: A Quality-Filtered Somali Web Corpus with a Matched Tokenizer and a Public Language-Identification Benchmark
SomaliWeb v1 delivers a cleaned Somali corpus, efficient BPE tokenizer, and side-by-side language identification benchmark while documenting defects in prior multilingual datasets.
-
Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings
Mixing auxiliary high-resource language data outperforms hyperparameter tuning in data-constrained bilingual pre-training, with gains equivalent to 2-13 times more unique target data.
-
Scaling Laws for Mixture Pretraining Under Data Constraints
Empirical study shows mixture pretraining tolerates higher target data repetition than single-source training, with a new repetition-aware scaling law enabling principled mixture selection based on data size, compute, and model scale.
-
moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT
Continued pretraining of ModernBERT on curated Portuguese data produces moBERTo, which reports top results on Portuguese retrieval reranking and PLUE-PT benchmarks.
-
Ishigaki-IDS: An Open-Weight Verifier-Aware Model for Information Delivery Specification Drafting in Building Information Modeling
Ishigaki-IDS is a verifier-aware LLM for generating validator-passing IDS files in BIM, reaching IDSAuditPass scores of 0.651-0.753 on a 166-case benchmark and cutting practitioner work time by 54.7%.
-
Mimir: Large-scale Multilingual Concept Modeling
Mimir is a 1.6B multilingual concept model pretrained on 38.9 billion sentences across 46 languages and instruction-tuned on 66.8 million sentences across 35 languages, then compared to a token-based LM of similar size.
-
Granite Embedding Multilingual R2 Models
Granite Embedding Multilingual R2 releases 311M and 97M parameter bi-encoder models that achieve state-of-the-art retrieval performance on multilingual text, code, long-document, and reasoning datasets.
-
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
GLM-4.5, a 355B-parameter MoE model with hybrid reasoning, scores 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified while ranking 3rd overall and 2nd on agentic benchmarks.