--- title: "Rosanne Liu — author profile and papers" description: "Rosanne Liu: 3 papers on Elamur Research (2019–2024), h-index 10 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/rosanne-liu/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/rosanne-liu/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Rosanne Liu # Rosanne Liu Rosanne Liu works on large pretrained language models, and in particular on how to steer, probe or strengthen them without rebuilding them. Liu's papers here span [text generation](https://md.research.elamur.ai/free/en/topics/text-generation/), [multilingual and cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) and [reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/). A common thread is leaving a pretrained model's weights untouched and adding something light around it: small attribute classifiers, carefully built prompts, or a search procedure that produces training signal. The most cited of these works is [Plug and Play Language Models](https://md.research.elamur.ai/free/en/papers/dathathri-2019-plug-play-language-models-simple/) (2019). It keeps GPT-2 frozen and controls attributes such as topic or sentiment. At each generation step, gradients from either a word list or a one-layer classifier adjust the model's cached activations, while extra terms keep the text fluent. [Language Models are Few-shot Multilingual Learners](https://md.research.elamur.ai/free/en/papers/winata-2021-language-models-are-few-shot/) (2021) asks whether models trained mostly on English can classify user intents in French, German and Spanish through in-context learning alone. It turns each intent into its own true/false question and compares the model's normalized confidence across classes. It also tests prompts whose English examples differ in language from the query. The newest paper, [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://md.research.elamur.ai/free/en/papers/luo-2024-improve-mathematical-reasoning-language-models/) (2024), moves to multi-step math. It addresses the cost of the step-by-step labels that process reward models need. Its method, OmegaPRM, is a divide-and-conquer Monte Carlo Tree Search that uses binary search to locate the first wrong step in a chain of reasoning. It reuses rollouts across the tree and keeps correct and incorrect examples balanced, starting only from questions and their reference answers. Bylines on these papers point to [Google](https://md.research.elamur.ai/free/en/companies/google/) in Mountain View from 2021 onward, and before that to Uber AI in San Francisco in 2018–2019. Recurring co-authors include [Jason Yosinski](https://md.research.elamur.ai/free/en/authors/jason-yosinski/) and [Andrea Madotto](https://md.research.elamur.ai/free/en/authors/andrea-madotto/). Other collaborators include [Sumanth Dathathri](https://md.research.elamur.ai/free/en/authors/sumanth-dathathri/), [Genta Indra Winata](https://md.research.elamur.ai/free/en/authors/genta-indra-winata/) and [Pascale Fung](https://md.research.elamur.ai/free/en/authors/pascale-fung/). All three papers here fall under [language models and pretraining](https://md.research.elamur.ai/free/en/topics/language-models/). Rosanne Liu has 3 papers in our library, in 2019–2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/), [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/); often with [Andrea Madotto](https://md.research.elamur.ai/free/en/authors/andrea-madotto/), [Jason Yosinski](https://md.research.elamur.ai/free/en/authors/jason-yosinski/), [Abhinav Rastogi](https://md.research.elamur.ai/free/en/authors/abhinav-rastogi/). 3 papers in our library · 2019–2024 [OpenAlex](https://openalex.org/A5062174486) · [**h-index 10**](https://openalex.org/authors/A5062174486) · [18 works](https://openalex.org/works?filter=author.id:A5062174486) · [919 citations](https://openalex.org/works?filter=author.id:A5062174486&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/rosanne-liu/#papers) · [🔗 743 citations in our library](https://md.research.elamur.ai/free/en/authors/rosanne-liu/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #2129](https://md.research.elamur.ai/free/en/paper-stars/page/22/#star-2129) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Rosanne+Liu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Rosanne+Liu) · [dblp](https://dblp.org/search?q=Rosanne+Liu) · [ACL Anthology](https://aclanthology.org/search/?q=Rosanne+Liu) ## Affiliations [🏢**Uber AI** San Francisco · United States 2018–2019 · 5 papers](https://ror.org/05vm0ed18) · [🏢**Google** Mountain View · United States 2021–2025 · 3 papers](https://md.research.elamur.ai/free/en/companies/google/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed. ## Topics [Language models & pretraining (3)](https://md.research.elamur.ai/free/en/topics/language-models/) · [Text generation (1)](https://md.research.elamur.ai/free/en/topics/text-generation/) · [Multilingual & cross-lingual NLP (1)](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Reasoning (1)](https://md.research.elamur.ai/free/en/topics/reasoning/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/papers/luo-2024-improve-mathematical-reasoning-language-models/) · [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/winata-2021-language-models-are-few-shot/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/dathathri-2019-plug-play-language-models-simple/) ## Papers The most cited first (OpenAlex and our library). 1. **[Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://md.research.elamur.ai/free/en/papers/dathathri-2019-plug-play-language-models-simple/)** *(2019 · 562 citations)* Large pretrained Transformer language models write fluent text, but steering what they produce, such as the topic or sentiment, usually means changing the architecture or retraining on labelled data. 2. **[Language Models are Few-shot Multilingual Learners](https://md.research.elamur.ai/free/en/papers/winata-2021-language-models-are-few-shot/)** *(2021 · 173 citations)* The paper asks whether large language models trained mostly on English can perform multi-class intent classification in other languages through in-context learning alone, with no parameter updates. 3. **[Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://md.research.elamur.ai/free/en/papers/luo-2024-improve-mathematical-reasoning-language-models/)** *(2024 · 163 citations)* Process Reward Models (PRMs) score each intermediate step of a solution. On multi-step math they help LLMs more than verifiers that judge only the final answer. The catch is the step-level labels PRMs need. Until now these came from paid human annotators or from brute-force Monte Carlo rollouts launched at every… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 10 co-authors with a page, the most papers together first. - [Andrea Madotto](https://md.research.elamur.ai/free/en/authors/andrea-madotto/) ×2 - [Jason Yosinski](https://md.research.elamur.ai/free/en/authors/jason-yosinski/) ×2 - [Abhinav Rastogi](https://md.research.elamur.ai/free/en/authors/abhinav-rastogi/) - [Genta Indra Winata](https://md.research.elamur.ai/free/en/authors/genta-indra-winata/) - [Lei Shu](https://md.research.elamur.ai/free/en/authors/lei-shu/) - [Pascale Fung](https://md.research.elamur.ai/free/en/authors/pascale-fung/) - [Sumanth Dathathri](https://md.research.elamur.ai/free/en/authors/sumanth-dathathri/) - [Yun Zhu](https://md.research.elamur.ai/free/en/authors/yun-zhu/) - [Yunxuan Li](https://md.research.elamur.ai/free/en/authors/yunxuan-li/) - [Zhaojiang Lin](https://md.research.elamur.ai/free/en/authors/zhaojiang-lin/) ## Cited by Papers of our library cite their works 743 times (of the 140,884 papers whose bibliographies we read); [59 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/rosanne-liu/cited-by/).