AI Paper Atlas

Research map / Benchmarks / QQP

QQP leaderboard

44 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on QQP. Best accuracy: 92.9 (HTLM-R3F-Prompt, ICLR 2022).

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.

QQP · accuracy

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

#accuracy ↑MethodPaperTopic
192.9HTLM-R3F-Prompt
BART-Large
HTLM: Hyper-Text Pre-Training and Prompting of Language Models
ICLR 2022 · GLUE results table
CLIP and zero-shot
292.5RoBERTa Large + AT + CTR
RoBERTa Large
Improved Text Classification via Contrastive Adversarial Training
AAAI 2022 · Table 2
Certified and empirical robustness
391.7LoRAM
DeBERTa-v3-base
The Primacy of Magnitude in Low-Rank Adaptation
NeurIPS 2025 · GLUE results table
Pruning and efficient tuning
491.68SUMO (SVD, rank=4)
RoBERTa-Base
SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training
NeurIPS 2025 · GLUE results table
Optimizers
591.4muTransfer
BERT-large
Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
NeurIPS 2021 · Table 6
Pruning and efficient tuning
691.29BERTTowards a Deep and Unified Understanding of Deep Neural Models in NLP
ICML 2019 · Table 2
Language, safety and interpretability
791.2ALBERT-base+BABN
ALBERT-base
Bayesian Attention Belief Networks
ICML 2021 · Table 1
Uncertainty and Gaussian processes
891.1DynaKD
6-layer BERT-style model
How to Trade Off the Quantity and Capacity of Teacher Ensemble: Learning Categorical Distribution to Stochastically Employ a Teacher for Distillation
AAAI 2024 · Table 5
Knowledge distillation
991.1StructBERT Base
BERT Base
StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
ICLR 2020 · Ablation over pre-training obj
Language, safety and interpretability
1091SIFT
RoBERTa-Large
Sparse is Enough in Fine-tuning Pre-trained Large Language Models
ICML 2024 · Table 1
Recognition and long-tail
23 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

QQP · F1

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

#F1 ↑MethodPaperTopic
189.1BERT6 best internal KD
BERTbase
Knowledge Distillation from Internal Representations
AAAI 2020 · Table 2
Knowledge distillation
288.68BOMF
RoBERTa-base
Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
NeurIPS 2024 · Table 1
Bayesian optimization
388.1DynaKD
6-layer BERT-style model
How to Trade Off the Quantity and Capacity of Teacher Ensemble: Learning Categorical Distribution to Stochastically Employ a Teacher for Distillation
AAAI 2024 · Table 5
Knowledge distillation
485.2SBM-Transformer
BERT variant
Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost
NeurIPS 2022 · GLUE results table
Attention and transformers
573.7RoBERTa^ASA
RoBERTa
Adversarial Self-Attention for Language Understanding
AAAI 2023 · Table 1
Attention and transformers
672.2LRC-BERT
BERT-base
LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding
AAAI 2021 · GLUE results table
RNNs and normalization
771.5FewGen
CTRL 1.6B; RoBERTa Large
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning
ICML 2023 · Main results table
Zero-/few-shot and meta-learning
871.4COSEE
BERT-base
COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism
AAAI 2025 · Table: Performance comparison
Test-time adaptation
971.3ROSITA
BERT_BASE
ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques
AAAI 2021 · Comparison with Existing Metho
Pruning and efficient tuning
1070.5BERT6-MixKD
BERT-base-uncased
MixKD: Towards Efficient Distillation of Large-scale Language Models
ICLR 2021 · GLUE test results table
Knowledge distillation
6 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.