Matthias Aßenmacher

56 papers A* 1B 2Journal 32Unranked 20

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Can Calibration of Positional Encodings Enhance Long Context Utilization? EACL (Findings) Tom Zehle, Matthias Aßenmacher
2026	J	`jnl`	The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices. CoRR Esteban Garces Arias, Nurzhan Sapargali, Christian Heumann, Matthias Aßenmacher
2026	—	`conf`	promptolution: A Unified, Modular Framework for Prompt Optimization. EACL (System Demonstrations) Tom Zehle, Timo Heiß, Moritz Schlager, Matthias Aßenmacher, Matthias Feurer
2025	—	`conf`	A Geoparsing Pipeline for Multilingual Social Media Posts from Ukraine. GeoExT@ECIR Maxim Mironov, Alexander Marquard, Daniel Racek, Christian Heumann, Paul W. Thurner, Matthias Aßenmacher
2025	—	`conf`	Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study. ACL (1) Bolei Ma, Berk Yoztyurk, Anna-Carolina Haensch, Xinpeng Wang, Markus Herklotz, Frauke Kreuter, Barbara Plank, Matthias Aßenmacher
2025	J	`jnl`	Are All Genders Equal in the Eyes of Algorithms? - Analysing Search and Retrieval Algorithms for Algorithmic Gender Fairness. CoRR Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher, Ludwig Bothmann, Christian Heumann, Stephanie Thiemichen
2025	—	`conf`	Are all Genders Equal in the Eyes of Algorithms? Analysing Search and Retrieval Algorithms for Algorithmic Gender Fairness. IC3K (KDIR) Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher, Ludwig Bothmann, Christian Heumann, Stephanie Thiemichen
2025	B	`conf`	Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation. COLING Esteban Garces Arias, Meimingwei Li, Christian Heumann, Matthias Aßenmacher
2025	J	`jnl`	Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corpora. CoRR Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher, Christian Heumann, Stephanie Thiemichen
2025	—	`conf`	GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation. EMNLP (Findings) Yuanhao Ding, Esteban Garces Arias, Meimingwei Li, Julian Rodemann, Matthias Aßenmacher, Danlu Chen, Gaojuan Fan, Christian Heumann, Chongsheng Zhang
2025	J	`jnl`	GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation. CoRR Yuanhao Ding, Esteban Garces Arias, Meimingwei Li, Julian Rodemann, Matthias Aßenmacher, Danlu Chen, Gaojuan Fan, Christian Heumann, Chongsheng Zhang
2025	J	`jnl`	Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan. CoRR Matthias Schöffel, Marinus Wiedner, Esteban Garces Arias, Paula Ruppert, Christian Heumann, Matthias Aßenmacher
2025	J	`jnl`	No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success. CoRR Lukas Rauch, Moritz Wirth, Denis Huseljic, Marek Herde, Bernhard Sick, Matthias Aßenmacher
2025	J	`jnl`	OBD-Finder: Explainable Coarse-to-Fine Text-Centric Oracle Bone Duplicates Discovery. CoRR Chongsheng Zhang, Shuwen Wu, Yingqi Chen, Matthias Aßenmacher, Christian Heumann, Yi Men, Gaojuan Fan, João Gama
2025	J	`jnl`	Reinforcement Learning for Latent-Space Thinking in LLMs. CoRR Enes Özeren, Matthias Aßenmacher
2025	J	`jnl`	Revisiting Active Learning under (Human) Label Variation. CoRR Cornelia Gruber, Helen Alber, Bernd Bischl, Göran Kauermann, Barbara Plank, Matthias Aßenmacher
2025	J	`jnl`	Statistical Multicriteria Evaluation of LLM-Generated Text. CoRR Esteban Garces Arias, Hannah Blocher, Julian Rodemann, Matthias Aßenmacher, Christoph Jansen
2025	J	`jnl`	Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages. CoRR Matthias Schöffel, Esteban Garces Arias, Marinus Wiedner, Paula Ruppert, Meimingwei Li, Christian Heumann, Matthias Aßenmacher
2025	J	`jnl`	promptolution: A Unified, Modular Framework for Prompt Optimization. CoRR Tom Zehle, Timo Heiß, Moritz Schlager, Matthias Aßenmacher, Matthias Feurer
2025	—	`conf`	taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades. ACL (Findings) Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher, Christian Heumann, Stephanie Thiemichen
2025	J	`jnl`	taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades. CoRR Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher, Christian Heumann, Stephanie Thiemichen
2024	J	`jnl`	AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers. CoRR Alexander Wuttke, Matthias Aßenmacher, Christopher Klamm, Max M. Lang, Quirin Würschinger, Frauke Kreuter
2024	—	`conf`	Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation. EMNLP (Findings) Esteban Garces Arias, Julian Rodemann, Meimingwei Li, Christian Heumann, Matthias Aßenmacher
2024	J	`jnl`	Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation. CoRR Esteban Garces Arias, Julian Rodemann, Meimingwei Li, Christian Heumann, Matthias Aßenmacher
2024	J	`jnl`	Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study. CoRR Bolei Ma, Berk Yoztyurk, Anna-Carolina Haensch, Xinpeng Wang, Markus Herklotz, Frauke Kreuter, Barbara Plank, Matthias Aßenmacher
2024	J	`jnl`	Can OpenSource beat ChatGPT? - A Comparative Study of Large Language Models for Text-to-Code Generation. CoRR Luis Mayer, Christian Heumann, Matthias Aßenmacher
2024	J	`jnl`	Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation. CoRR Esteban Garces Arias, Meimingwei Li, Christian Heumann, Matthias Aßenmacher
2024	—	`conf`	Divergent Token Metrics: Measuring degradation to prune away LLM components - and optimize quantization. NAACL-HLT Björn Deiseroth, Max Meuer, Nikolas Gritsch, Constantin Eichenberg, Patrick Schramowski, Matthias Aßenmacher, Kristian Kersting
2024	J	`jnl`	From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Tasks. CoRR Andreas Stephan, Dawei Zhu, Matthias Aßenmacher, Xiaoyu Shen, Benjamin Roth
2024	—	`conf`	Introducing wwm-german-18k - Can LLMs Crack the Million? (Or Win at Least 500 Euros?). ICNLSP Matthias Aßenmacher, Luis Karrlein, Philipp Schiele, Christian Heumann
2024	J	`jnl`	Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework. CoRR Esteban Garces Arias, Hannah Blocher, Julian Rodemann, Meimingwei Li, Christian Heumann, Matthias Aßenmacher
2023	—	`conf`	A tailored Handwritten-Text-Recognition System for Medieval Latin. ALP@RANLP Philipp Koch, Gilary Vera Nuñez, Esteban Garces Arias, Christian Heumann, Matthias Schöffel, Alexander Häberlin, Matthias Aßenmacher
2023	J	`jnl`	A tailored Handwritten-Text-Recognition System for Medieval Latin. CoRR Philipp Koch, Gilary Vera Nuñez, Esteban Garces Arias, Christian Heumann, Matthias Schöffel, Alexander Häberlin, Matthias Aßenmacher
2023	—	`conf`	ActiveGLAE: A Benchmark for Deep Active Learning with Transformers. ECML/PKDD (1) Lukas Rauch, Matthias Aßenmacher, Denis Huseljic, Moritz Wirth, Bernd Bischl, Bernhard Sick
2023	J	`jnl`	ActiveGLAE: A Benchmark for Deep Active Learning with Transformers. CoRR Lukas Rauch, Matthias Aßenmacher, Denis Huseljic, Moritz Wirth, Bernd Bischl, Bernhard Sick
2023	A*	`conf`	Automatic Transcription of Handwritten Old Occitan Language. EMNLP Esteban Garces Arias, Vallari Pai, Matthias Schöffel, Christian Heumann, Matthias Aßenmacher
2023	J	`jnl`	Classifying multilingual party manifestos: Domain transfer across country, time, and genre. CoRR Matthias Aßenmacher, Nadja Sauter, Christian Heumann
2023	J	`jnl`	Divergent Token Metrics: Measuring degradation to prune away LLM components - and optimize quantization. CoRR Björn Deiseroth, Max Meuer, Nikolas Gritsch, Constantin Eichenberg, Patrick Schramowski, Matthias Aßenmacher, Kristian Kersting
2023	J	`jnl`	How Different Is Stereotypical Bias Across Languages? CoRR Ibrahim Tolga Öztürk, Rostislav Nedelchev, Christian Heumann, Esteban Garces Arias, Marius Roger, Bernd Bischl, Matthias Aßenmacher
2023	—	`conf`	How Different is Stereotypical Bias Across Languages? PKDD/ECML Workshops (1) Ibrahim Tolga Öztürk, Rostislav Nedelchev, Christian Heumann, Esteban Garces Arias, Marius Roger, Bernd Bischl, Matthias Aßenmacher
2023	—	`conf`	How Prevalent Is Gender Bias in ChatGPT? - Exploring German and English ChatGPT Responses. PKDD/ECML Workshops (1) Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher, Christian Heumann, Stephanie Thiemichen
2023	J	`jnl`	How Prevalent is Gender Bias in ChatGPT? - Exploring German and English ChatGPT Responses. CoRR Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher, Christian Heumann, Stephanie Thiemichen
2023	J	`jnl`	Multimodal Deep Learning. CoRR Cem Akkus, Luyang Chu, Vladana Djakovic, Steffen Jauch-Walser, Philipp Koch, Giacomo Loss, Christopher Marquardt, Marco Moldovan, Nadja Sauter, Maximilian Schneider, Rickmer Schulte, Karol Urbanczyk, Jann Goschenhofer, Christian Heumann, Rasmus Hvingelby, Daniel Schalk, Matthias Aßenmacher
2023	—	`conf`	Towards Enhancing Deep Active Learning with Weak Supervision and Constrained Clustering. IAL@PKDD/ECML Matthias Aßenmacher, Lukas Rauch, Jann Goschenhofer, Andreas Stephan, Bernd Bischl, Benjamin Roth, Bernhard Sick
2022	—	`conf`	On the Current State of Reproducibility and Reporting of Uncertainty for Aspect-Based Sentiment Analysis. ECML/PKDD (2) Elisabeth Lebmeier, Matthias Aßenmacher, Christian Heumann
2022	—	`conf`	Pre-trained language models evaluating themselves - A comparative study. Insights@ACL Philipp Koch, Matthias Aßenmacher, Christian Heumann
2021	—	`conf`	A New Benchmark for NLP in Social Sciences: Evaluating the Usefulness of Pre-trained Language Models for Classifying Open-ended Survey Responses. ICAART (2) Maximilian Meidinger, Matthias Aßenmacher
2021	J	`jnl`	Benchmarking down-scaled (not so large) pre-trained language models. CoRR Matthias Aßenmacher, Patrick Schulze, Christian Heumann
2021	—	`—`	Comparability, evaluation and benchmarking of large pre-trained language models. Matthias Aßenmacher
2021	J	`jnl`	Exploring Topic-Metadata Relationships with the STM: A Bayesian Approach. CoRR Patrick Schulze, Simon Wiegrebe, Paul W. Thurner, Christian Heumann, Matthias Aßenmacher, Sandra Wankmüller
2021	—	`conf`	Re-Evaluating GermEval17 Using German Pre-Trained Language Models. SwissText Matthias Aßenmacher, Alessandra Corvonato, Christian Heumann
2021	J	`jnl`	Re-Evaluating GermEval17 Using German Pre-Trained Language Models. CoRR Matthias Aßenmacher, Alessandra Corvonato, Christian Heumann
2020	B	`conf`	Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News. COLING Maike Guderlei, Matthias Aßenmacher
2020	—	`conf`	On the Comparability of Pre-trained Language Models. SwissText/KONVENS Matthias Aßenmacher, Christian Heumann
2020	J	`jnl`	On the comparability of Pre-trained Language Models. CoRR Matthias Aßenmacher, Christian Heumann
2020	J	`jnl`	Pre-trained language models as knowledge bases for Automotive Complaint Analysis. CoRR V. D. Viellieber, Matthias Aßenmacher