ToaST uses vocabulary-independent split trees and integer programming to produce tokenizers with over 11% fewer tokens than BPE, WordPiece, and UnigramLM while improving 1.5B-parameter LM scores on CORE.
In: Erk, K., Smith, N.A
8 Pith papers cite this work, alongside 147 external citations. Polarity classification is still indexing.
8
Pith papers citing it
147
external citations · OpenAlex
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
Synthetic data improves models only in information-open generation-training loops with external signals, and coarser signals like binary correctness enable better generalization by converging to the most information-efficient component.
SLoW selects low-frequency word dictionaries to boost LLM translation quality and efficiency across 100 languages from FLORES.
A multi-stage pipeline that pivots Traditional Mongolian script through Cyrillic before translation improves MT quality across multiple backbones and target languages, and generates useful synthetic parallel data.
An ensemble of per-language fine-tuned Gemma 3 models with three synthetic data strategies and per-language threshold tuning achieves 2nd place overall in SemEval-2026 Task 9 with mean macro-F1 of 0.811.
A literature survey that organizes prompting, fine-tuning, preference optimization, and context-aware techniques for LLM-based machine translation with emphasis on low-resource languages.
citing papers explorer
-
Tokenization with Split Trees
ToaST uses vocabulary-independent split trees and integer programming to produce tokenizers with over 11% fewer tokens than BPE, WordPiece, and UnigramLM while improving 1.5B-parameter LM scores on CORE.
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
An Information-Theoretic Criterion for Efficient Data Synthesis
Synthetic data improves models only in information-open generation-training loops with external signals, and coarser signals like binary correctness enable better generalization by converging to the most information-efficient component.
-
SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models
SLoW selects low-frequency word dictionaries to boost LLM translation quality and efficiency across 100 languages from FLORES.
-
CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Script
A multi-stage pipeline that pivots Traditional Mongolian script through Cyrillic before translation improves MT quality across multiple backbones and target languages, and generates useful synthetic parallel data.
-
PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation
An ensemble of per-language fine-tuned Gemma 3 models with three synthetic data strategies and per-language threshold tuning achieves 2nd place overall in SemEval-2026 Task 9 with mean macro-F1 of 0.811.
-
Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation
A literature survey that organizes prompting, fine-tuning, preference optimization, and context-aware techniques for LLM-based machine translation with emphasis on low-resource languages.
- Faster Superword Tokenization