Pith. sign in

REVIEW 24 cited by

mT5: A massively multilingual pre-trained text-to-text transformer

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.11934 v3 pith:6XBLTDCH submitted 2020-10-22 cs.CL

classification cs.CL
keywords multilingualtext-to-textmodelpre-trainedstate-of-the-arttransformeraccidentalattain
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages. We detail the design and modified training of mT5 and demonstrate its state-of-the-art performance on many multilingual benchmarks. We also describe a simple technique to prevent "accidental translation" in the zero-shot setting, where a generative model chooses to (partially) translate its prediction into the wrong language. All of the code and model checkpoints used in this work are publicly available.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 24 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. On the Fitness Landscape in the $NK$ Model

    math.PR 2025-08 unverdicted novelty 7.0 of 10

    For the NK fitness landscape with K/N tending to alpha, exact limits for free energy and maximum fitness are identified, together with the geometry of near-fittest peaks.

  2. Meta CLIP 2: A Worldwide Scaling Recipe

    cs.CV 2025-07 conditional novelty 7.0 of 10

    A data curation and training recipe that scales CLIP from English-only data to 300+ languages from scratch, breaking the curse of multilinguality at ViT-H/14 scale.

  3. Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks

    cs.CL 2025-07 reject novelty 7.0 of 10

    The paper creates a span-level Chinese hate speech dataset and a 830-term coded hate lexicon, but its two-stage training method's reported superiority is contradicted by the paper's own COLD results.

  4. Effective vocabulary expansion of multilingual language models for extremely low-resource languages

    cs.CL 2026-02 conditional novelty 6.0 of 10

    Using bilingual-dictionary-aligned embeddings to initialize expanded vocabulary improves mBERT continued pre-training for seven low-resource languages, with average gains of 0.54% (POS) and 2.60% (NER).

  5. Evaluating LLMs on Chinese Idiom Translation

    cs.CL 2025-08 unverdicted novelty 6.0 of 10

    Across 900 annotated translation pairs from nine MT systems, the best system still mistranslates Chinese idioms in 28% of cases, and standard metrics miss these errors (Pearson correlation below 0.48).

  6. Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries

    cs.CR 2025-08 conditional novelty 6.0 of 10

    CEMA converts multi-task black-box text attacks into attacks on a binary classifier trained on cluster pseudo-labels, achieving high attack success with 100 queries.

  7. Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan

    cs.AI 2025-08 conditional novelty 6.0 of 10

    Multi-TW is the first Traditional Chinese benchmark to evaluate multimodal models on both image-text and audio-text questions while also measuring inference latency.

  8. FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

    cs.CL 2025-06 conditional novelty 6.0 of 10

    An adaptive, per-language data filtering and deduplication pipeline produces multilingual LLM pre-training corpora that beat prior public datasets on 11 of 14 evaluated languages, and a 20TB, 1,868 language-script dat...

  9. Cost-Optimal Active AI Model Evaluation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    The paper derives budget-optimal rules for mixing cheap weak raters and expensive strong raters so that the mean rating is estimated with minimum variance, and shows large cost savings when example difficulty varies.

  10. OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion

    cs.IR 2025-06 conditional novelty 6.0 of 10

    A unified encoder-decoder model with prefix representation enhancement and reward-weighted DPO outperforms Kuaishou's online multi-stage query suggestion system in offline and live A/B evaluations.

  11. Entity Image and Mixed-Modal Image Retrieval Datasets

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A new benchmark, MMIR, built from Wikipedia and WIT by masking entity names and supplying canonical entity images, tests mixed-modal retrieval with single- and multi-entity queries.

  12. MultimodalHugs: Enabling Sign Language Processing in Hugging Face

    cs.CL 2025-09 conditional novelty 5.0 of 10

    MultimodalHugs provides a standardized TSV-based dataset format, modular processors, and Hugging Face integration to enable reproducible sign language and multimodal translation experiments.

  13. Two Spelling Normalization Approaches Based on Large Language Models

    cs.CL 2025-06 conditional novelty 5.0 of 10

    Fine-tuned mT5 and mBART perform competitively on Spanish and Slovene historical spelling normalization, but character-based SMT achieves the best overall scores, confirming its continued state-of-the-art status.

  14. Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages

    cs.CL 2025-06 conditional novelty 5.0 of 10

    Generating Python programs as intermediate guidance before SQL, then voting on Python execution results to select the fastest matching SQL, improves text-to-SQL execution accuracy and efficiency on BIRD and Archer.

  15. Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages

    cs.CL 2025-05 conditional novelty 5.0 of 10

    MSumBench is a new English/Chinese benchmark that grades summaries across six domains on faithfulness, completeness, and conciseness, using domain-specific key-facts and multi-agent-debate-assisted human annotations, ...

  16. Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model

    cs.CL 2025-05 reject novelty 5.0 of 10

    A compact 1.5B Arabic-English model beats GPT-4o mini only on the authors' own Tarjama-25 benchmark, while trailing large models on standard WMT24++ and IWSLT2017 tests.

  17. SELF: Self-Extend the Context Length With Logistic Growth Function

    cs.CL 2025-05 conditional novelty 5.0 of 10

    SELF replaces Self-Extend's fixed token grouping with a logistic-growth grouping schedule, giving mixed but sometimes large gains on long-context benchmarks.

  18. LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization

    cs.CL 2025-05 conditional novelty 5.0 of 10

    LAGO shows that constraining alignment matrices of linguistically similar languages to be close improves few-shot cross-lingual embedding inversion accuracy over independent per-language baselines.

  19. Beyond English: The Impact of Prompt Translation Strategies across Languages and Tasks in Multilingual LLMs

    cs.CL 2025-02 conditional novelty 5.0 of 10

    Selective pre-translation, translating only some prompt components into English, generally outperforms both full prompt translation and direct inference across tasks and languages, with the largest gains for low-resou...

  20. DIRECT: Direct Decoding for Efficient and Aligned Sequence Labeling with Large Language Models

    cs.CL 2026-07 conditional novelty 4.0 of 10

    DPO after SFT plus constrained template-filling decoding improves LLM sequence-labeling accuracy and cuts inference time by reusing KV cache for non-label tokens.

  21. Rethinking Indic AI from a Lens of Cultural Heritage Preservation

    cs.AI 2026-07 conditional novelty 4.0 of 10

    The paper surveys Indic NLP evolution and proposes 'Culture Sensing' to integrate indigenous oral knowledge into foundation models for cultural preservation.

  22. SHAMI-MT: A Syrian Arabic Dialect to Modern Standard Arabic Bidirectional Machine Translation System

    cs.CL 2025-08 conditional novelty 4.0 of 10

    A bidirectional MSA-Syrian Arabic translation system built by fine-tuning AraT5v2 on the Nabra corpus; only the MSA-to-Shami direction is evaluated, with a GPT-4.1 score of 4.01/5.

  23. Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models

    cs.CL 2025-06 reject novelty 3.0 of 10

    Forcing a language model to output only the allowed answer-letter tokens, with a tuned penalty, recovers accuracy lost to a single extra space in multiple-choice prompts.

  24. Prompt, Translate, Fine-Tune, Re-Initialize, or Instruction-Tune? Adapting LLMs for In-Context Learning in Low-Resource Languages

    cs.CL 2025-06

Pith tools