Large Language Models

Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models EMNLP 2022 QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillation EMNLP 2022 Re2G: Retrieve, Rerank, Generate NAACL 2022 Read before Generate! Faithful Long Form Question Answering with Machine Reading ACL 2022 Reducing Disambiguation Biases in NMT by Leveraging Explicit Word Sense Information NAACL 2022 Residual Language Model for End-to-end Speech Recognition Interspeech 2022 Rethinking Data Augmentation in Text-to-text Paradigm COLING 2022 Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? EMNLP 2022 Show, Don’t Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue NAACL 2022 SKILL: Structured Knowledge Infusion for Large Language Models NAACL 2022 STaR: Bootstrapping Reasoning With Reasoning NeurIPS 2022 Subject Verb Agreement Error Patterns in Meaningless Sentences: Humans vs. BERT COLING 2022 Summarizing Patients’ Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models COLING 2022 Systematicity in GPT-3’s Interpretation of Novel English Noun Compounds EMNLP 2022 Taking Actions Separately: A Bidirectionally-Adaptive Transfer Learning Method for Low-Resource Neural Machine Translation COLING 2022 Testing Large Language Models on Compositionality and Inference with Phrase-Level Adjective-Noun Entailment COLING 2022 The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset NeurIPS 2022 The COVID That Wasn’t: Counterfactual Journalism Using GPT COLING 2022 The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models EMNLP 2022 The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models NeurIPS 2022 Thinking about GPT-3 In-Context Learning for Biomedical IE? Think Again EMNLP 2022 Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding EMNLP 2022 Vega-MT: The JD Explore Academy Machine Translation System for WMT22 EMNLP 2022 Visual Commonsense in Pretrained Unimodal and Multimodal Models NAACL 2022 What Language Model to Train if You Have One Million GPU Hours? EMNLP 2022