🧑‍🔬 Vera Schmitt

🏛️ Affiliations

🎓Technische Universität BerlinBerlin · Germany2020–2026 · 59 papersEducationEmployment 2020–2024 · Researcher, Quality & Usability LabEmployment 2024–2026 · Head of XplaiNLP Research Group, Institute of Software Engineering and Theoretical Computer Sciencecurrent🔬German Research Centre for Artificial IntelligenceKaiserslautern · Germany2023–2026 · 25 papersEmployment since 2023 · Guest Researcher, SLTcurrent🎓Johannes Gutenberg University MainzMainz · Germany2026Employment since 2026 · Professor, XplaiNLP Group🎓Tel Aviv UniversityTel Aviv · Israel2022Education 2022 · Research Stay, Dep. of Industrial Engineering🎓Leuphana University of LüneburgLüneburg · Germany2016–2019Education 2016–2019 · M.Sc. Data Science🎓University of KonstanzKonstanz · Germany2012–2016Education 2012–2016 · B.A. Politics and Public Administration, Additional Subject: Statistics

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Persona Prompting as a Lens on LLM Social Reasoning (2026 · 2 citations)
   The paper asks whether persona prompting (PP), where an LLM is told to answer as someone with given demographic traits, changes the word-level rationales it gives along with its labels, and whether those simulated viewpoints match real human annotators.
2. Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall (2026 · 2 citations)
   The paper asks how post-training weight quantization affects factual knowledge recall (FKR), meaning an LLM's ability to retrieve facts stored during pretraining.
3. From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence (2026 · 1 citation)
   Professional fact-checks contain detailed evidence and reasoning, but this material is buried in free-form prose, so automated verification systems rarely reuse it.
4. From Weights to Activations: Is Steering the Next Frontier of Adaptation? (2026 · 1 citation)
   Steering means changing a language model's behavior by editing its internal activations during inference. It has mostly been treated as an interpretability tool, so it is rarely compared with established ways of adapting LLMs. Ostermann et al. argue in this position paper that steering is itself an adaptation…
5. Retrieving Climate Change Disinformation by Narrative (2026 · 1 citation)
   Climate disinformation narratives are usually detected by classifiers built on fixed taxonomies, so new storylines go unnoticed.
6. Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas (2026)
   Detecting propaganda in short social media posts is difficult. The texts are brief and noisy, and human annotators often disagree. Existing taxonomies list rhetorical devices such as loaded language. The authors instead propose an intent-based scheme that groups techniques by the strategic goal behind a message, such…
7. hermeneutichools at SemEval-2026 Task 4: Multiperspectivity as a Resource for Narrative Similarity Prediction (2026)
   The paper addresses SemEval-2026 Task 4 (Track A). Each item is an anchor story and two candidate stories, and a system must pick the candidate closer to the anchor. The authors treat the existence of several valid readings of a narrative as something a model can use, not a defect of the benchmark.
8. News Credibility Assessment by LLMs and Humans: Implications for Political Bias (2026)
   The paper asks whose viewpoint LLMs reflect when they judge news outlets. Earlier work compared model ratings only with expert ratings. Here the authors also compare them with public opinion split by political camp. They built a dataset of 47 outlets, 27 from the U.S. and 20 from Germany. Each outlet has expert…
9. Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation (2026)
   Counterfactual explanations are small edits to an input that flip a classifier's prediction. LLMs produce them well in English, but their quality in other languages had not been studied. To examine this, the authors evaluate three open instruction-tuned LLMs on XNLI and SIB200, two multilingual classification…
10. Selective Multimodal Retrieval for Automated Verification of Image–Text Claims (2026)
    Text-based fact-checking pipelines often fail when misinformation pairs a statement with an image. Fully multimodal systems handle such claims but are expensive and can behave unpredictably. For the FEVER-9 shared task, the authors built a pipeline that decides deliberately where visual information is used, instead…
11. Take It All: Ensemble Retrieval for Multimodal Evidence Aggregation (2026)
    Fact-checking claims that pair text with images, such as miscaptioned photos or fabricated infographics, requires analyzing both modalities.

🤝 Co-authors here

12 of 20 co-authors with a page, the most papers together first.

• Sebastian Möller ×6
• Veronika Solopova ×6
• Charlott Jakob ×5
• Max Upravitelev ×5
• Premtim Sahitaj ×5
• Ariana Sahitaj ×4
• Nils Feldhus ×3
• Hinrich Schuetze ×2
• Jing Yang ×2
• Qianli Wang ×2
• Simon Ostermann ×2
• Christin Seifert

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026 ×2
• Fact Extraction and VERification Workshop (FEVER) ×2: FEVER 2026 ×2
• Conference of the European Chapter of the Association for Computational Linguistics (EACL): EACL 2026
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Language Resources and Evaluation Conference (LREC): LREC 2026
• Workshop on Ecology, Environment, and Natural Language Processing: Workshop on Ecology, Environment, and Natural Language Processing 2026
• International Workshop on Semantic Evaluation (SemEval): SemEval 2026
• Workshop on Trustworthy NLP: Workshop on Trustworthy NLP 2026
• Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis: Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis 2026

🔗 Cited by

Papers of our library cite their works 1 time (of the 149,439 papers whose bibliographies we read).

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/vera-schmitt/