AI Paper Atlas

Research map / Benchmarks / SciTail

SciTail leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SciTail. Best accuracy: 96.8 (CA-MTL, ICLR 2021).

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.

SciTail · accuracy

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

#accuracy ↑MethodPaperTopic
196.8CA-MTL
RoBERTa-LARGE
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data
ICLR 2021 · Table, CA-MTL test performance
Continual fine-tuning of LLMs
295.7Unified-IO XLUNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks
ICLR 2023 · Table 4
Human and embodied modeling
394.12BERT(RMIB)
BERT
RMIB: Representation Matching Information Bottleneck for Matching Text Representations
ICML 2024 · Table 1
Recognition and long-tail
492.9R²-Net
BERT-base
Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching
AAAI 2021 · Table: Experimental Results (a
Recognition and long-tail
592.43PDB
T5-base
Weight matrices compression based on PDB model in deep neural networks
ICML 2025 · Table 7
Matrix and tensor methods
690.68KES + BERT+match-LSTM
BERT+match-LSTM
Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks
AAAI 2020 · Table 1
Knowledge and temporal graphs
786.3SINN (1200D)Generalize Sentence Representation with Self-Inference
AAAI 2020 · Table 2
Language, safety and interpretability
885.2NLISys
match-LSTM (GRU)
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
AAAI 2019 · Table 1
Retrieval and knowledge
983.6D-ATT + CoDACompositional De-Attention Networks
NeurIPS 2019 · Table 3
Attention and transformers
1081.1RCRNRecurrently Controlled Recurrent Networks
NeurIPS 2018 · Table 5
RNNs and normalization
3 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.