--- title: "Wenhan Xiong — author profile and papers" description: "Wenhan Xiong, Meta: 3 papers on Elamur Research (2020–2023), h-index 21 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/wenhan-xiong/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/wenhan-xiong/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Wenhan Xiong # Wenhan Xiong Wenhan Xiong works on natural language processing, with a focus on how systems read and reason over large or mixed bodies of evidence. Their papers here address [question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) that has to combine facts from several sources, the evaluation of models on naturally long documents, and the adaptation of [language models](https://md.research.elamur.ai/free/en/topics/language-models/) so they can use much longer inputs. Much of the work builds benchmarks: it collects or curates tasks that existing methods handle poorly, then uses them to measure progress. The most cited of these papers is [HybridQA](https://md.research.elamur.ai/free/en/papers/chen-2020-hybridqa-dataset-multi-hop-question/), a crowdsourced dataset for multi-hop question answering. Each question rests on a Wikipedia table together with the articles linked from its cells, and it is written so that neither the table nor the text answers it alone. This tests whether a system can move between structured and unstructured knowledge, where earlier hybrid evaluations had simply masked parts of knowledge-base datasets. The more recent papers turn to long inputs. [SCROLLS](https://md.research.elamur.ai/free/en/papers/shaham-2022-scrolls-standardized-comparison-over-long/) (2022) gathers existing datasets of genuinely long texts, covering summarization, question answering and inference across several domains, so that efficient transformer variants can be compared on real language rather than on perplexity or artificially stretched inputs. [Effective Long-Context Scaling of Foundation Models](https://md.research.elamur.ai/free/en/papers/xiong-2023-effective-long-context-scaling-foundation/) (2023) presents Llama 2 Long, made by continuing to pretrain Llama 2 on long sequences. Its only architectural change is a larger RoPE base frequency, and a low-cost instruction-tuning stage adds synthetic question answering over long documents. Xiong is currently at [Meta](https://md.research.elamur.ai/free/en/companies/meta/). Earlier papers came from the [University of California, Santa Barbara](https://md.research.elamur.ai/free/en/universities/university-of-california-santa-barbara/), along with work at [IBM](https://md.research.elamur.ai/free/en/companies/ibm/) (United States) and [Tel Aviv University](https://md.research.elamur.ai/free/en/universities/tel-aviv-university/). Co-authors on the papers here include [Jonathan Berant](https://md.research.elamur.ai/free/en/authors/jonathan-berant/), Mor Geva, Maor Ivgi, [Barlas Oguz](https://md.research.elamur.ai/free/en/authors/barlas-oguz/), Madian Khabsa and Louis Martin. Wenhan Xiong has 3 papers in our library, in 2020–2023, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/); often with [Adi Haviv](https://md.research.elamur.ai/free/en/authors/adi-haviv/), [Ankit Gupta](https://md.research.elamur.ai/free/en/authors/ankit-gupta/), [Avia Efrat](https://md.research.elamur.ai/free/en/authors/avia-efrat/). 3 papers in our library · 2020–2023 current affiliation [Meta](https://md.research.elamur.ai/free/en/companies/meta/) · Menlo Park United States [OpenAlex](https://openalex.org/A5110635444) · [**h-index 21**](https://openalex.org/authors/A5110635444) · [61 works](https://openalex.org/works?filter=author.id:A5110635444) · [3,100 citations](https://openalex.org/works?filter=author.id:A5110635444&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works in our library](https://md.research.elamur.ai/free/en/authors/wenhan-xiong/#papers) · [1,591 citations in our library](https://md.research.elamur.ai/free/en/authors/wenhan-xiong/cited-by/) · 2 more works in our library · [⭐ Paper Star rank #2439](https://md.research.elamur.ai/free/en/paper-stars/page/25/#star-2439) 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=Wenhan+Xiong) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Wenhan+Xiong) · [dblp](https://dblp.org/search?q=Wenhan+Xiong) · [ACL Anthology](https://aclanthology.org/search/?q=Wenhan+Xiong) ## Affiliations [🏢**Meta** Menlo Park · United States 2022–2025 · 8 papers*current*](https://md.research.elamur.ai/free/en/companies/meta/) · [🎓**University of California, Santa Barbara** Santa Barbara · United States 2017–2021 · 29 papers](https://md.research.elamur.ai/free/en/universities/university-of-california-santa-barbara/) · [🏢**IBM** Armonk · United States 2018–2019 · 5 papers](https://md.research.elamur.ai/free/en/companies/ibm/) · [🎓**Tel Aviv University** Tel Aviv · Israel 2022 · 2 papers](https://md.research.elamur.ai/free/en/universities/tel-aviv-university/) · [🎓**Princeton University** Princeton · United States 2021 · 2 papers](https://md.research.elamur.ai/free/en/universities/princeton-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed. ## Topics [Language models & pretraining 1](https://md.research.elamur.ai/free/en/topics/language-models/) · [Question answering 1](https://md.research.elamur.ai/free/en/topics/question-answering/) ## Works by year ### 2020s [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/xiong-2023-effective-long-context-scaling-foundation/) · [**2022** 1 paper](https://md.research.elamur.ai/free/en/papers/shaham-2022-scrolls-standardized-comparison-over-long/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/chen-2020-hybridqa-dataset-multi-hop-question/) ## Papers The most cited first (OpenAlex and our library). 1. **[HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://md.research.elamur.ai/free/en/papers/chen-2020-hybridqa-dataset-multi-hop-question/)** *(2020 · 376 citations)* Most QA benchmarks draw evidence from one source type, either free text or structured data such as knowledge bases and tables. 2. **[Effective Long-Context Scaling of Foundation Models](https://md.research.elamur.ai/free/en/papers/xiong-2023-effective-long-context-scaling-foundation/)** *(2023 · 177 citations)* In 2023, strong long-input handling was mostly available through proprietary APIs. Earlier open attempts to extend context were usually judged only by perplexity or synthetic probes, and they often lost quality on short tasks. This Meta paper introduces Llama 2 Long, a family of 7B–70B models built by continuing to… 3. **[SCROLLS: Standardized CompaRison Over Long Language Sequences](https://md.research.elamur.ai/free/en/papers/shaham-2022-scrolls-standardized-comparison-over-long/)** *(2022 · 162 citations)* Most NLP benchmarks use sentences or short paragraphs. Meanwhile, many efficient transformer variants built for long inputs lack a common way to be compared on real language. Perplexity mostly rewards local prediction, and Long Range Arena contains only two natural-language tasks, which are stretched artificially… ## Also in our library 2 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 19 co-authors with a page, the most papers together first. - [Adi Haviv](https://md.research.elamur.ai/free/en/authors/adi-haviv/) - [Ankit Gupta](https://md.research.elamur.ai/free/en/authors/ankit-gupta/) - [Avia Efrat](https://md.research.elamur.ai/free/en/authors/avia-efrat/) - [Barlas Oguz](https://md.research.elamur.ai/free/en/authors/barlas-oguz/) - [Han Fang](https://md.research.elamur.ai/free/en/authors/han-fang/) - [Hong Wang](https://md.research.elamur.ai/free/en/authors/hong-wang/) - [Jingyu Liu](https://md.research.elamur.ai/free/en/authors/jingyu-liu/) - [Jonathan Berant](https://md.research.elamur.ai/free/en/authors/jonathan-berant/) - [Louis Martin](https://md.research.elamur.ai/free/en/authors/louis-martin/) - [Madian Khabsa](https://md.research.elamur.ai/free/en/authors/madian-khabsa/) - [Maor Ivgi](https://md.research.elamur.ai/free/en/authors/maor-ivgi/) - [Mor Geva](https://md.research.elamur.ai/free/en/authors/mor-geva/) ## Cited by Papers of our library cite their works 1,591 times (of the 140,884 papers whose bibliographies we read); [116 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/wenhan-xiong/cited-by/).