--- title: "Iryna Gurevych — papers, page 4 — Elamur Research" description: "Iryna Gurevych, Technische Universität Darmstadt: 86 papers on Elamur Research (2010–2026), h-index 71 — affiliations, topics, co-authors…" canonical: "https://research.elamur.ai/free/en/authors/iryna-gurevych/page/4/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/iryna-gurevych/page/4/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Iryna Gurevych](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/) / page 4 # Iryna Gurevych · page 4 86 papers in our library · 2010–2026 · page 4 of 4 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/page/3/) [1](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/) [2](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/page/2/) [3](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/page/3/) **4** 76. **[Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework](https://md.research.elamur.ai/free/en/papers/dycke-2026-automatic-reviewers-fail-detect-faulty/)** *(2026 · 5 citations)* LLMs are increasingly used as automatic review generators (ARGs), but studies of their quality disagree. One reason is that these evaluations mix many reviewing skills and often ignore publication context. Dycke and Gurevych isolate one skill that depends only on the paper itself: checking whether results… 77. **[Can LLMs Automate Fact-Checking Article Writing?](https://md.research.elamur.ai/free/en/papers/sahnan-2026-can-llms-automate-fact-checking/)** *(2026 · 5 citations)* Research on automated fact-checking usually ends at spotting claims, retrieving evidence, assigning a verdict and, at most, producing a short justification. 78. **[How Quantization Shapes Bias in Large Language Models](https://md.research.elamur.ai/free/en/papers/marcuzzi-2026-how-quantization-shapes-bias-large/)** *(2026 · 3 citations)* Quantization is a common way to shrink LLMs for deployment, but its effect on social bias has received little systematic study. 79. **[Protecting multimodal large language models against misleading visualizations](https://md.research.elamur.ai/free/en/papers/tonglet-2026-protecting-multimodal-large-language-models/)** *(2026 · 3 citations)* Charts can distort their underlying data through design flaws called misleaders, such as truncated or inverted axes, dual axes, or 3D effects. 80. **[Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review](https://md.research.elamur.ai/free/en/papers/ruan-2026-author-loop-response-generation-evaluation/)** *(2026 · 2 citations)* Authors draw on knowledge only they have when answering peer reviewers, such as planned clarifications, new experiments and design reasons. 81. **[Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue](https://md.research.elamur.ai/free/en/papers/purkayastha-2026-decision-making-deliberation-meta-reviewing/)** *(2026 · 2 citations)* The paper reframes meta-reviewing as a decision-making task rather than a summarization task. In this view, a dialogue agent answers the meta-reviewer's questions about the reviews. It can contrast reviewer opinions, help weigh arguments and place them in context, but it never volunteers verdicts. The authors set two… 82. **[Aligned Probing: Relating Toxic Behavior and Model Internals](https://md.research.elamur.ai/free/en/papers/waldis-2026-aligned-probing-relating-toxic-behavior/)** *(2026 · 1 citation)* Work on LM toxicity usually judges models only by what they generate and treats toxicity as one uniform category. 83. **[Is this chart lying to me? Automating the detection of misleading visualizations](https://md.research.elamur.ai/free/en/papers/tonglet-2026-is-this-chart-lying-me/)** *(2026 · 1 citation)* Charts that break design conventions, for example through truncated axes or misleading 3D effects, can distort data and spread misinformation online. 84. **[Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity](https://md.research.elamur.ai/free/en/papers/liu-2026-tailored-emotional-llm-supporter-enhancing/)** *(2026 · 1 citation)* LLMs are increasingly used for emotional support, but it is unclear whether their replies respect the cultural context of a person in distress. 85. **[LLMs as Cultural Archives: Cultural Commonsense Knowledge Graph Extraction](https://md.research.elamur.ai/free/en/papers/tonga-2026-llms-as-cultural-archives-cultural/)** *(2026)* The paper asks whether the cultural knowledge that large language models absorb during pretraining can be turned into an explicit, structured resource. 86. **[Reward Modeling for Scientific Writing Evaluation](https://md.research.elamur.ai/free/en/papers/sahinuc-2026-reward-modeling-scientific-writing-evaluation/)** *(2026)* The paper tackles the automatic evaluation of scientific writing, where off-the-shelf LLM judges and general-purpose reward models tend to misapply task-specific criteria and rubrics and to make assumptions beyond them. [← prev](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/page/3/) [1](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/) [2](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/page/2/) [3](https://md.research.elamur.ai/free/en/authors/iryna-gurevych/page/3/) **4**