Large Language Models

How Gender Debiasing Affects Internal Model Representations, and Why It Matters NAACL 2022 How Much Do Modifications to Transformer Language Models Affect Their Ability to Learn Linguistic Knowledge? ACL 2022 How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis ACL 2022 HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification EMNLP 2022 HSE at TempoWiC: Detecting Meaning Shift in Social Media with Diachronic Language Models EMNLP 2022 HTLM: Hyper-Text Pre-Training and Prompting of Language Models ICLR 2022 HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea NAACL 2022 Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention IJCAI 2022 HyperPrompt: Prompt-based Task-Conditioning of Transformers ICML 2022 IDPG: An Instance-Dependent Prompt Generation Method NAACL 2022 Impact of Pretraining Term Frequencies on Few-Shot Numerical Reasoning EMNLP 2022 Improving In-Context Few-Shot Learning via Self-Supervised Training NAACL 2022 Improving Robustness of Language Models from a Geometry-aware Perspective ACL 2022 Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models EMNLP 2022 Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Change EMNLP 2022 InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation AAAI 2022 Input-specific Attention Subnetworks for Adversarial Detection ACL 2022 Interpreting the Robustness of Neural NLP Models to Textual Perturbations ACL 2022 Introducing QuBERT: A Large Monolingual Corpus and BERT Model for Southern Quechua NAACL 2022 Investigating Math Word Problems using Pretrained Multilingual Language Models EMNLP 2022 Is a Question Decomposition Unit All We Need? EMNLP 2022 Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text ACL 2022 Iteratively Prompt Pre-trained Language Models for Chain of Thought EMNLP 2022 JAKET: Joint Pre-training of Knowledge Graph and Language Understanding AAAI 2022 Japanese ASR-Robust Pre-trained Language Model with Pseudo-Error Sentences Generated by Grapheme-Phoneme Conversion Interspeech 2022