--- title: "Lingpeng Kong — author profile and papers" description: "Lingpeng Kong, City University of Hong Kong: 8 papers on Elamur Research (2014–2024), h-index 15 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/lingpeng-kong/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/lingpeng-kong/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Lingpeng Kong # Lingpeng Kong Lingpeng Kong works on natural language processing, and their papers here run from syntactic analysis of text to the training and evaluation of large language models. The earlier work concerns [dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/), including how to obtain Stanford dependencies efficiently without first building constituent trees. The later work asks what pre-trained models can do and how to measure it fairly. It builds benchmarks and datasets, compares systems across many languages and tasks, and looks at faster ways to generate text, such as diffusion models for sequence-to-sequence problems. The most cited paper here, [Multilingual Machine Translation with Large Language Models](https://md.research.elamur.ai/free/en/papers/zhu-2024-multilingual-machine-translation-large-language/) (2024), tests eight LLMs prompted in context on 102 languages and 606 translation directions. It sets their output against supervised systems such as NLLB and Google Translate. [A Dependency Parser for Tweets](https://md.research.elamur.ai/free/en/papers/aclbulk-2014-kong-dependency-parser-tweets/) (2014) adapts parsing to social media text. That work handles tokens with no syntactic role, several utterances within one tweet, and multiword names. [ZeroGen](https://md.research.elamur.ai/free/en/papers/ye-2022-zerogen-efficient-zero-shot-learning/) (2022) has a pre-trained model write a labelled training set, so that a small model can do zero-shot tasks without querying the large one at inference. [L-Eval](https://md.research.elamur.ai/free/en/papers/an-2023-l-eval-instituting-standardized-evaluation/) (2023) offers a hand-checked benchmark of 20 sub-tasks for long-context models and studies how well automatic metrics agree with human judgement. The newest papers, from 2024, turn to robustness and multimodal understanding. [GSM-Plus](https://md.research.elamur.ai/free/en/papers/li-2024-gsm-plus-comprehensive-benchmark-evaluating/) adds perturbed versions of grade-school maths problems to test whether models reason or lean on surface patterns. [Multimodal ArXiv](https://md.research.elamur.ai/free/en/papers/li-2024-multimodal-arxiv-dataset-improving-scientific/) builds training data from arXiv preprints to help vision-language models read scientific figures and diagrams. Kong is based at the University of Hong Kong, with papers from there between 2021 and 2026. Earlier bylines include Carnegie Mellon University (2016–2017), Google and the Shanghai Artificial Intelligence Laboratory. Co-authors on these papers include [Noah A. Smith](https://md.research.elamur.ai/free/en/authors/noah-a-smith/), [Shansan Gong](https://md.research.elamur.ai/free/en/authors/shansan-gong/), Jiangtao Feng, Zhiyong Wu and Qintong Li. 8 papers on this site · 2014–2024 current affiliation [City University of Hong Kong](https://md.research.elamur.ai/free/en/universities/city-university-of-hong-kong/), Hong Kong, Hong Kong; [Peking University](https://md.research.elamur.ai/free/en/universities/peking-university/), Beijing, China; [University of Hong Kong](https://md.research.elamur.ai/free/en/universities/university-of-hong-kong/), Pok Fu Lam, Hong Kong Lingpeng Kong has 8 papers on this site, in 2014–2024, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Dependency parsing](https://md.research.elamur.ai/free/en/topics/dependency-parsing/), [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/); often with [Jiangtao Feng](https://md.research.elamur.ai/free/en/authors/jiangtao-feng/), [Lei Li](https://md.research.elamur.ai/free/en/authors/lei-li/), [Mukai Li](https://md.research.elamur.ai/free/en/authors/mukai-li/). 2 of them are among the papers [Mova](https://md.research.elamur.ai/free/en/projects/mova/) reads. [OpenAlex](https://openalex.org/A5101497114) · [ORCID](https://orcid.org/0000-0002-9407-7193) · [**h-index 15**](https://openalex.org/authors/A5101497114) · [93 works](https://openalex.org/works?filter=author.id:A5101497114) · [1 226 citations](https://openalex.org/works?filter=author.id:A5101497114&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [8 works on this site](https://md.research.elamur.ai/free/en/authors/lingpeng-kong/#papers) · [1 547 citations in our library](https://md.research.elamur.ai/free/en/authors/lingpeng-kong/cited-by/) · 10 more works in our library 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=Lingpeng+Kong) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Lingpeng+Kong) · [dblp](https://dblp.org/search?q=Lingpeng+Kong) · [ACL Anthology](https://aclanthology.org/search/?q=Lingpeng+Kong) ## Affiliations - [University of Hong Kong](https://md.research.elamur.ai/free/en/universities/university-of-hong-kong/) · Pok Fu Lam, Hong Kong —current · 2021–2026 on 59 papers - [City University of Hong Kong](https://md.research.elamur.ai/free/en/universities/city-university-of-hong-kong/) · Hong Kong, Hong Kong —current · 2026 on 1 paper - [Peking University](https://md.research.elamur.ai/free/en/universities/peking-university/) · Beijing, China —current · 2026 on 1 paper - [Google (United States)](https://md.research.elamur.ai/free/en/companies/google/) · Mountain View, United States —2019–2024 on 4 papers - [Shanghai Artificial Intelligence Laboratory](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) · Shanghai, China —2021–2022 on 5 papers - [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · Pittsburgh, United States —2016–2017 on 3 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 more institutions on single bylines are not listed. ## Topics [Language models & pretraining 3](https://md.research.elamur.ai/free/en/topics/language-models/) · [Dependency parsing 1](https://md.research.elamur.ai/free/en/topics/dependency-parsing/) · [Machine translation 1](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Multilingual & cross-lingual NLP 1](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Evaluation & benchmarks 1](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Reasoning 1](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Vision & language 1](https://md.research.elamur.ai/free/en/topics/multimodal/) ## Works by year ### 2020s [**2024** 3 papers](https://md.research.elamur.ai/free/en/authors/lingpeng-kong/year/2024/) · [**2023** 2 papers](https://md.research.elamur.ai/free/en/authors/lingpeng-kong/year/2023/) · [**2022** 1 paper](https://md.research.elamur.ai/free/en/papers/ye-2022-zerogen-efficient-zero-shot-learning/) ### 2010s [**2014** 2 papers](https://md.research.elamur.ai/free/en/authors/lingpeng-kong/year/2014/) ## Papers The most cited first (OpenAlex and our library). 1. **[Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://md.research.elamur.ai/free/en/papers/zhu-2024-multilingual-machine-translation-large-language/)** *(2024 · 503 citations)* This paper examines how well large language models handle multilingual machine translation (MMT) and which factors shape that ability. 2. **[A Dependency Parser for Tweets](https://md.research.elamur.ai/free/en/papers/aclbulk-2014-kong-dependency-parser-tweets/)** *(2014 · 298 citations)* Tweets break the assumptions of newswire parsers: many tokens (retweet markers, usernames, hashtags, URLs, punctuation) have no syntactic role, a tweet can hold several utterances with their own roots, and multiword names and idioms are common. 3. **[ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://md.research.elamur.ai/free/en/papers/ye-2022-zerogen-efficient-zero-shot-learning/)** *(2022 · 242 citations)* The paper asks whether zero-shot NLP can avoid running a huge pre-trained language model (PLM) at inference time. 4. **[L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://md.research.elamur.ai/free/en/papers/an-2023-l-eval-instituting-standardized-evaluation/)** *(2023 · 159 citations)* Open-source long context language models (LCLMs) are multiplying, but the field lacks a careful, shared way to test them. 5. **[Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models](https://md.research.elamur.ai/free/en/papers/li-2024-multimodal-arxiv-dataset-improving-scientific/)** *(2024 · 123 citations)* Open-source large vision-language models (LVLMs) handle natural photos well but often fail on abstract visuals such as scientific plots and geometric diagrams. 6. **[GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers](https://md.research.elamur.ai/free/en/papers/li-2024-gsm-plus-comprehensive-benchmark-evaluating/)** *(2024 · 107 citations)* LLMs now score very high on GSM8K, with GPT-4 above 90%, yet small edits to a problem often make them fail. 7. **[An Empirical Comparison of Parsing Methods for Stanford Dependencies](https://md.research.elamur.ai/free/en/papers/enud-2014-kong-empirical-comparison-parsing-methods-stanford/)** *(2014 · 39 citations)* Stanford dependencies are usually obtained by parsing to constituents and then applying head rules (c-parsing), which is slow. 8. **[DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models](https://md.research.elamur.ai/free/en/papers/gong-2023-diffuseq-v2-bridging-discrete-continuous/)** *(2023 · 32 citations)* Seq2Seq text diffusion models such as DiffuSeq produce good text, but they train slowly and generate slowly. They also usually rely on Minimum Bayes Risk (MBR) decoding over several samples to reach good quality. DiffuSeq-v2 speeds up both training and generation by combining continuous and discrete noise. ## Also in our library 10 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 12 of 26 co-authors with a page, the most papers together first. - [Jiangtao Feng](https://md.research.elamur.ai/free/en/authors/jiangtao-feng/) ×2 - [Lei Li](https://md.research.elamur.ai/free/en/authors/lei-li/) ×2 - [Mukai Li](https://md.research.elamur.ai/free/en/authors/mukai-li/) ×2 - [Noah A. Smith](https://md.research.elamur.ai/free/en/authors/noah-a-smith/) ×2 - [Qintong Li](https://md.research.elamur.ai/free/en/authors/qintong-li/) ×2 - [Shansan Gong](https://md.research.elamur.ai/free/en/authors/shansan-gong/) ×2 - [Zhiyong Wu](https://md.research.elamur.ai/free/en/authors/zhiyong-wu/) ×2 - [Archna Bhatia](https://md.research.elamur.ai/free/en/authors/archna-bhatia/) - [Chris Dyer](https://md.research.elamur.ai/free/en/authors/chris-dyer/) - [Hongyi Liu](https://md.research.elamur.ai/free/en/authors/hongyi-liu/) - [Jiajun Chen](https://md.research.elamur.ai/free/en/authors/jiajun-chen/) - [Jingjing Xu](https://md.research.elamur.ai/free/en/authors/jingjing-xu/) ## Cited by Papers of our library cite their works 1 547 times (of the 140 884 papers whose bibliographies we read); [104 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/lingpeng-kong/cited-by/).