Pith. sign in

REVIEW 7 cited by

LongT5: Efficient Text-To-Text Transformer for Long Sequences

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 2112.07916 v2 pith:BYHXV6YF submitted 2021-12-15 cs.CL

LongT5: Efficient Text-To-Text Transformer for Long Sequences

classification cs.CL
keywords attentionmodelglobalincreasinginputlengthlongt5mechanism
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models. In this paper, we present a new model, called LongT5, with which we explore the effects of scaling both the input length and model size at the same time. Specifically, we integrated attention ideas from long-input transformers (ETC), and adopted pre-training strategies from summarization pre-training (PEGASUS) into the scalable T5 architecture. The result is a new attention mechanism we call {\em Transient Global} (TGlobal), which mimics ETC's local/global attention mechanism, but without requiring additional side-inputs. We are able to achieve state-of-the-art results on several summarization tasks and outperform the original T5 models on question answering tasks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

    cs.LG 2024-07 accept novelty 7.0

    FlashAttention-3 achieves 1.5-2x speedup on H100 GPUs for attention, reaching 740 TFLOPs/s (75% utilization) in FP16 and near 1.2 PFLOPs/s in FP8 while cutting numerical error by 2.6x versus baseline FP8 attention.

  2. MoBA: Mixture of Block Attention for Long-Context LLMs

    cs.LG 2025-02 unverdicted novelty 6.0

    MoBA routes attention over blocks via MoE-style gating to enable dynamic, bias-light long-context attention that matches full attention performance at lower cost.

  3. A BART-based approach with hierarchical strategy for Vietnamese abstractive multi-document summarization

    cs.CL 2026-06 unverdicted novelty 5.0

    A BART-based hierarchical approach with golden-summary-driven document shortening achieves ROUGE2-F1 of 0.2468 on the VLSP 2022 Vietnamese multi-document summarization task and releases additional training data.

  4. DTCRS: Dynamic Tree Construction for Recursive Summarization

    cs.CL 2026-04 unverdicted novelty 5.0

    DTCRS dynamically builds summary trees only for suitable question types by using sub-question embeddings as cluster centers, cutting construction time while improving QA on three tasks.

  5. The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

    cs.AI 2026-06 unverdicted novelty 2.0

    A comprehensive reference book organizing existing techniques for agentic AI systems across LLM substrate, reasoning, agent design patterns, inter-agent coordination, and production deployment.

  6. A Comprehensive Overview of Large Language Models

    cs.CL 2023-07 unverdicted novelty 2.0

    A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.

  7. The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

    cs.AI 2026-06 unverdicted novelty 1.0

    A survey-style reference book mapping the full agentic-AI stack from transformer internals to production deployment, with no new research result.