GPT-3 shows that scaling an autoregressive language model to 175 billion parameters enables strong few-shot performance across diverse NLP tasks via in-context prompting without fine-tuning.
hub
arXiv preprint arXiv:1511.06709 , year=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
abstract
Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only using parallel data for training. Target-side monolingual data plays an important role in boosting fluency for phrase-based statistical machine translation, and we investigate the use of monolingual data for NMT. In contrast to previous work, which combines NMT models with separately trained language models, we note that encoder-decoder NMT architectures already have the capacity to learn the same information as a language model, and we explore strategies to train with monolingual data without changing the neural network architecture. By pairing monolingual training data with an automatic back-translation, we can treat it as additional parallel training data, and we obtain substantial improvements on the WMT 15 task English<->German (+2.8-3.7 BLEU), and for the low-resourced IWSLT 14 task Turkish->English (+2.1-3.4 BLEU), obtaining new state-of-the-art results. We also show that fine-tuning on in-domain monolingual and parallel data gives substantial improvements for the IWSLT 15 task English->German.
hub tools
citation-role summary
background 1
other 1
citation-polarity summary
representative citing papers
ClassEval-Pro benchmark shows frontier LLMs achieve at most 45.6% Pass@1 on class-level code tasks, with logic errors (56%) and dependency errors (38%) as dominant failure modes.
KL regularization aligning model predictions with empirical transition patterns improves macro-F1 by 9-42% in next dialogue act prediction on German counselling data and transfers to other datasets.
Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
REACT uses a RAG-powered attacker to generate challenging adversarial examples and trains a detector with contrastive learning in an alternating loop, raising average F1 by 4.95 points and lowering attack success rate by 3.66 points across tested settings.
LLMs corrupt an average of 25% of document content during long delegated editing workflows across 52 domains, even frontier models, and agentic tools do not mitigate the issue.
A single multilingual NMT model for 103 languages trained on 25B examples demonstrates transfer learning benefits for low-resource languages.
Development of domain-specific scientific corpora for English-Spanish, English-French, and English-Portuguese and their application to fine-tuning NMT models.
The paper surveys data-centric strategies for foundation models in computational healthcare and supplies a curated list of related models and datasets.
Baidu-OSU WMT19 system achieves >10 BLEU gain on En-Fr and Fr-En social media translation via domain sensitive training and pseudo noisy sources.
citing papers explorer
-
Language Models are Few-Shot Learners
GPT-3 shows that scaling an autoregressive language model to 175 billion parameters enables strong few-shot performance across diverse NLP tasks via in-context prompting without fine-tuning.
-
ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation
ClassEval-Pro benchmark shows frontier LLMs achieve at most 45.6% Pass@1 on class-level code tasks, with logic errors (56%) and dependency errors (38%) as dominant failure modes.
-
Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations
KL regularization aligning model predictions with empirical transition patterns improves macro-F1 by 9-42% in next dialogue act prediction on German counselling data and transfers to other datasets.
-
Self-Rewarding Language Models
Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.
-
ART: Automatic multi-step reasoning and tool-use for large language models
ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.
-
Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training
REACT uses a RAG-powered attacker to generate challenging adversarial examples and trains a detector with contrastive learning in an alternating loop, raising average F1 by 4.95 points and lowering attack success rate by 3.66 points across tested settings.
-
LLMs Corrupt Your Documents When You Delegate
LLMs corrupt an average of 25% of document content during long delegated editing workflows across 52 domains, even frontier models, and agentic tools do not mitigate the issue.
-
Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
A single multilingual NMT model for 103 languages trained on 25B examples demonstrates transfer learning benefits for low-resource languages.
-
Enhancing Scientific Discourse: Machine Translation for the Scientific Domain
Development of domain-specific scientific corpora for English-Spanish, English-French, and English-Portuguese and their application to fine-tuning NMT models.
-
Data-Centric Foundation Models in Computational Healthcare: A Survey
The paper surveys data-centric strategies for foundation models in computational healthcare and supplies a curated list of related models and datasets.
-
Robust Machine Translation with Domain Sensitive Pseudo-Sources: Baidu-OSU WMT19 MT Robustness Shared Task System Report
Baidu-OSU WMT19 system achieves >10 BLEU gain on En-Fr and Fr-En social media translation via domain sensitive training and pseudo noisy sources.