--- title: "Quoc Viet Le — papers, page 2 — Elamur Research" description: "Quoc Viet Le: 34 papers on Elamur Research (2014–2025), h-index 118 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/quoc-viet-le/page/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/quoc-viet-le/page/2/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Quoc Viet Le](https://md.research.elamur.ai/free/en/authors/quoc-viet-le/) / page 2 # Quoc Viet Le · page 2 34 papers in our library · 2014–2025 · page 2 of 2 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/quoc-viet-le/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/quoc-viet-le/) [1](https://md.research.elamur.ai/free/en/authors/quoc-viet-le/) **2** 26. **[Unsupervised Pretraining for Sequence to Sequence Learning](https://md.research.elamur.ai/free/en/papers/ramachandran-2017-unsupervised-pretraining-sequence-sequence-learning/)** *(2017 · 327 citations)* Seq2seq networks tend to overfit when labeled data is scarce. The authors propose a simple way to use unlabeled text to address this. They train two language models on monolingual data, one for the source language and one for the target language. These LMs supply the initial weights for the embeddings and first LSTM… 27. **[Carbon Emissions and Large Neural Network Training](https://md.research.elamur.ai/free/en/papers/patterson-2021-carbon-emissions-large-neural-network/)** *(2021 · 323 citations)* The paper asks how much electricity and greenhouse-gas output (CO2e) the training of large NLP models actually requires. 28. **[Multi-task Sequence to Sequence Learning](https://md.research.elamur.ai/free/en/papers/luong-2015-multi-task-sequence-sequence-learning/)** *(2015 · 321 citations)* Sequence-to-sequence (seq2seq) models had mostly been trained for one task at a time. The authors ask whether training them jointly on several related tasks helps. They define three ways to share parameters. In one-to-many, a single encoder feeds several task-specific decoders, such as translation and constituency… 29. **[BAM! Born-Again Multi-Task Networks for Natural Language Understanding](https://md.research.elamur.ai/free/en/papers/clark-2019-bam-born-again-multi-task/)** *(2019 · 285 citations)* Multi-task neural models in NLP often fail to match the accuracy of separately trained single-task models. 30. **[Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://md.research.elamur.ai/free/en/papers/brown-2024-large-language-monkeys-scaling-inference/)** *(2024 · 270 citations)* At inference time, LLMs are usually given only one attempt per problem. This paper asks whether extra inference compute is well spent on drawing many independent samples per problem and keeping the best one. The authors split the question in two. Coverage asks whether any sample solves the problem. Precision asks… 31. **[Long-form factuality in large language models](https://md.research.elamur.ai/free/en/papers/wei-2024-long-form-factuality-large-language/)** *(2024 · 165 citations)* Large language models often make factual mistakes when they write answers several paragraphs long. Before this work there was no broad benchmark for this, and no cheap way to score such answers at scale. The Google DeepMind authors address the problem with three components. The first is LongFact, a set of 2,280… 32. **[SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://md.research.elamur.ai/free/en/papers/chu-2025-sft-memorizes-rl-generalizes-comparative/)** *(2025 · 160 citations)* Foundation models are usually post-trained with supervised fine-tuning (SFT), reinforcement learning (RL), or both. 33. **[Effective Domain Mixing for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/britz-2017-effective-domain-mixing-neural-machine/)** *(2017 · 156 citations)* NMT systems are often trained on pooled data from very different sources, but simply concatenating such corpora can lower quality on each individual domain. 34. **[FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://md.research.elamur.ai/free/en/papers/vu-2023-freshllms-refreshing-large-language-models/)** *(2023 · 134 citations)* LLMs are usually trained once and then frozen, so they struggle with questions whose answers depend on recent events or rest on false assumptions. [← prev](https://md.research.elamur.ai/free/en/authors/quoc-viet-le/) [1](https://md.research.elamur.ai/free/en/authors/quoc-viet-le/) **2**