| CAPO: Cost-Aware Prompt Optimization | ✓ Link | 62.27 | | Llama-3.3-70B + CAPO | 2025-04-22 |
| An Algorithm for Routing Vectors in Sequences | ✓ Link | 59.8 | | Heinsen Routing + RoBERTa Large | 2022-11-20 |
| Self-Explaining Structures Improve NLP Models | ✓ Link | 59.1 | | RoBERTa-large+Self-Explaining | 2020-12-03 |
| An Algorithm for Routing Capsules in All Domains | ✓ Link | 58.5 | | Heinsen Routing + GPT-2 | 2019-11-02 |
| Improved Sentence Modeling using Suffix Bidirectional LSTM | | 56.2 | | BCN+Suffix BiLSTM-Tied+CoVe | 2018-05-18 |
| Fine-grained Sentiment Classification using BERT | ✓ Link | 55.5 | | BERT Large | 2019-10-04 |
| LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning | ✓ Link | 54.9 | | LM-CPPF RoBERTa-base | 2023-05-29 |
| Deep contextualized word representations | ✓ Link | 54.7 | | BCN+ELMo | 2018-02-15 |
| A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors | ✓ Link | 54.6 | | byte mLSTM7 | 2018-05-14 |
| Learned in Translation: Contextualized Word Vectors | ✓ Link | 53.7 | | BCN+Char+CoVe | 2017-08-01 |
| Cell-aware Stacked LSTMs for Modeling Sentences | | 53.6 | | Bi-CAS-LSTM | 2018-09-07 |
| Convolutional Neural Networks with Recurrent Neural Filters | ✓ Link | 53.4 | | CNN-RNF-LSTM | 2018-08-28 |
| Fine-grained Sentiment Classification using BERT | ✓ Link | 53.2 | | BERT Base | 2019-10-04 |
| Star-Transformer | ✓ Link | 53.0 | | Star-Transformer | 2019-02-25 |
| BP-Transformer: Modelling Long-Range Context via Binary Partitioning | ✓ Link | 52.71 | | BP-Transformer + GloVe | 2019-11-11 |
| A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification | | 51.4 | | MEAN | 2018-07-13 |
| Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks | ✓ Link | 51.0 | | Constituency Tree-LSTM | 2015-02-28 |
| Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models | | 50.4 | | Bi-LSTM+2+5 | 2018-12-04 |
| Message Passing Attention Networks for Document Understanding | ✓ Link | 49.68 | | MPAD-path | 2019-08-17 |
| Less Grammar, More Features | ✓ Link | 49.6 | | Epic | 2014-06-01 |
| Sentiment Analysis by Capsules | ✓ Link | 49.3 | | RNN-Capsule | 2018-02-01 |
| A C-LSTM Neural Network for Text Classification | ✓ Link | 49.2 | | C-LSTM | 2015-11-27 |
| The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learning | ✓ Link | 49.14 | | STM+TSED+PT+2L | 2019-05-31 |
| Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms | ✓ Link | 46.1 | | SWEM-concat | 2018-05-24 |
| All-but-the-Top: Simple and Effective Postprocessing for Word Representations | ✓ Link | 45.02 | | GRU-RNN-WORD2VEC | 2017-02-05 |
| Exploring Joint Neural Model for Sentence Level Discourse Parsing and Sentiment Analysis | | 44.82 | | Joined Model Multi-tasking | 2017-08-01 |
| Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank | ✓ Link | 44.4 | | MV-RNN | 2013-10-01 |
| Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training | ✓ Link | 43.6 | | GloVe+Emo2Vec | 2018-09-12 |
| Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training | ✓ Link | 41.6 | | Emo2Vec | 2018-09-12 |
| CAPO: Cost-Aware Prompt Optimization | ✓ Link | | 60.2 | Mistral-Small-24B + CAPO | 2025-04-22 |
| CAPO: Cost-Aware Prompt Optimization | ✓ Link | | 59.07 | Qwen2.5-32B + CAPO | 2025-04-22 |