Large Language Models

Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training EMNLP 2022 Revisiting Parameter-Efficient Tuning: Are We Really There Yet? EMNLP 2022 Scientific and Creative Analogies in Pretrained Language Models EMNLP 2022 Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse NeurIPS 2022 SLING: Sino Linguistic Evaluation of Large Language Models EMNLP 2022 Sort by Structure: Language Model Ranking as Dependency Probing NAACL 2022 Symbolic Knowledge Distillation: from General Language Models to Commonsense Models NAACL 2022 Synchromesh: Reliable Code Generation from Pre-trained Language Models ICLR 2022 Systematicity in GPT-3’s Interpretation of Novel English Noun Compounds EMNLP 2022 TAPEX: Table Pre-training via Learning a Neural SQL Executor ICLR 2022 Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection NAACL 2022 Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction NeurIPS 2022 TestAug: A Framework for Augmenting Capability-based NLP Tests COLING 2022 Testing Large Language Models on Compositionality and Inference with Phrase-Level Adjective-Noun Entailment COLING 2022 Testing the Ability of Language Models to Interpret Figurative Language NAACL 2022 Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models NeurIPS 2022 The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning NeurIPS 2022 Topicalization in Language Models: A Case Study on Japanese COLING 2022 Towards a Progression-Aware Autonomous Dialogue Agent NAACL 2022 Towards a Unified View of Parameter-Efficient Transfer Learning ICLR 2022 Towards Coherent and Consistent Use of Entities in Narrative Generation ICML 2022 Towards Continual Knowledge Learning of Language Models ICLR 2022 Towards Few-Shot Identification of Morality Frames using In-Context Learning EMNLP 2022 Towards Tracing Knowledge in Language Models Back to the Training Data EMNLP 2022 Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space EMNLP 2022