Itisha Yadav, Sirko Schindler, Diana Peters, and Roman Klinger. External knowledge integration in large language models: A survey on methods, challenges, and future directions. Semantic Web Journal, 2026. accepted. [ bib | http ]

Jeremy Barnes, Valentin Barriere, Orphée De Clercq, Roman Klinger, Célia Nouri, Debora Nozza, and Pranaydeep Singh, editors. The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026), Rabat, Morocco, March 2026. Association for Computational Linguistics. [ bib | http ]

Lynn Greschner, Sabine Weber, and Roman Klinger. Trust me, i can convince you: The contextualized argument appraisal framework and the contarga corpus. In Proceedings of the Language Resources and Evaluation Conference, Palma de Mallorca, Spain, May 2026. European Language Resources Association. [ bib | arXiv | http | .pdf ]

Yarik Menchaca Resendiz and Roman Klinger. Parl: Prompt-based agents for reinforcement learning. In Proceedings of the Language Resources and Evaluation Conference, Palma de Mallorca, Spain, May 2026. European Language Resources Association. accepted. [ bib | arXiv | http | .pdf ]

Lynn Greschner, Meike Bauer, Sabine Weber, and Roman Klinger. Categorical emotions or appraisals – which emotion model explains argument convincingness better? In Proceedings of the Language Resources and Evaluation Conference, Palma de Mallorca, Spain, May 2026. European Language Resources Association. accepted. [ bib | arXiv | http | .pdf ]

Egil Rønningstad, Roman Klinger, Lilja Øvrelid, and Erik Velldal. Entity-level sentiment analysis with sentence relevance detection. In Proceedings of the Language Resources and Evaluation Conference, Palma de Mallorca, Spain, May 2026. European Language Resources Association. accepted. [ bib | .pdf ]

Johannes Schäfer and Roman Klinger. Disambiguation of emotion annotations by contextualizing events in plausible narratives. In Proceedings of the Language Resources and Evaluation Conference, Palma de Mallorca, Spain, May 2026. European Language Resources Association. accepted. [ bib | arXiv | http | .pdf ]

Sabine Weber, Lynn Greschner, and Roman Klinger. Less is more? the role of demographic author information in emotion classification of ambiguous text. In Proceedings of the Language Resources and Evaluation Conference, Palma de Mallorca, Spain, May 2026. European Language Resources Association. accepted. [ bib | .pdf ]

Johannes Schäfer, Janne Wagner, and Roman Klinger. Appraisal trajectories in narratives reveal distinct patterns of emotion evocation. In Jeremy Barnes, Valentin Barriere, Orphée De Clercq, Roman Klinger, Célia Nouri, Debora Nozza, and Pranaydeep Singh, editors, The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026), pages 73--82, Rabat, Morocco, March 2026. Association for Computational Linguistics. [ bib | http | .pdf ]

Sabine Weber, Lynn Greschner, and Roman Klinger. Says who? argument convincingness and reader stance are correlated with perceived author personality. In Jeremy Barnes, Valentin Barriere, Orphée De Clercq, Roman Klinger, Célia Nouri, Debora Nozza, and Pranaydeep Singh, editors, The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media Analysis (WASSA 2026), pages 265--277, Rabat, Morocco, March 2026. Association for Computational Linguistics. accepted. [ bib | http | .pdf ]

Yanran Chen, Lynn Greschner, Roman Klinger, Michael Klenk, and Steffen Eger. Emotionally charged, logically blurred: AI-driven emotional framing impairs human fallacy detection. In Vera Demberg, Kentaro Inui, and Lluís Marquez, editors, Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6709--6732, Rabat, Morocco, March 2026. Association for Computational Linguistics. [ bib | arXiv | http ]

Aswathy Velutharambath, Kai Sassenberg, and Roman Klinger. What if deception cannot be detected? a cross-linguistic study on the limits of deception detection from text. Computational Linguistics, 2026. in print. [ bib | DOI | arXiv | http ]