AI Paper Atlas

Research map / Benchmarks / Gigaword

Gigaword leaderboard

20 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Gigaword. Best ROUGE-1: 45.7 (GENIE, ICML 2023).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Gigaword · ROUGE-1

18 papers, each with its best reported number for its own method; higher is better.

#ROUGE-1 ↑MethodPaperTopic
145.7GENIEText Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph Denoise
ICML 2023 · Table 2
Autoregressive and latent generation
240.45BART+R3F
BART
Better Fine-Tuning by Reducing Representational Collapse
ICLR 2021 · Summarization results table
Pruning and efficient tuning
339.81OFAOFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
ICML 2022 · Table: Gigaword
Cross-modal learning
439.19Beam+BPNorm (c=0.55)
BERT-Base (uncased)
Controlling the Amount of Verbatim Copying in Abstractive Summarization
AAAI 2020 · Summarization results on the G
Language, safety and interpretability
538.82TaiLr
BART-base
Tailoring Language Generation Models under Total Variation Distance
ICLR 2023 · Table 3
Fast diffusion sampling
637.97Pointer-Generator + MacNet
Pointer-Generator
MacNet: Transferring Knowledge from Machine Comprehension to Sequence-to-Sequence Models
NeurIPS 2018 · Table 2
Language, safety and interpretability
737.4LevT distillation
Transformer base
Levenshtein Transformer
NeurIPS 2019 · Table 1
Molecules and proteins
837.2MLE+OTRLSequence Generation with Optimal-Transport-Enhanced Reinforcement Learning
AAAI 2020 · Table 4
Offline RL
936.78HATSExploring Human-Like Reading Strategy for Abstractive Text Summarization
AAAI 2019 · Table 2
Language, safety and interpretability
1036.44Ours
Difformer
Discrete Modeling via Boundary Conditional Diffusion Processes
NeurIPS 2024 · Language modeling results tabl
Fast diffusion sampling
8 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Gigaword · ROUGE-2

15 papers, each with its best reported number for its own method; higher is better.

5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Gigaword · ROUGE-L

15 papers, each with its best reported number for its own method; higher is better.

5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.