The NLP Group continuously looks for computer science students at Leibniz University Hannover who would like write their bachelor's or master's thesis in the area of natural language processing.
Topics
All thesis topics should be related to the main research directions of the NLP Group, which include steering of LLMs, computational argumentation, educational NLP, advanced learning methods in NLP, bias detection and mitigation, and social XAI.
Below, we provide a selection of currently available topics. Details of the topics are discussed and shaped jointly in the beginning of the thesis process. Other topics are possible, including own ideas from the student's side, if they go hand in hand with our research interests. Please note that the exact topic of your thesis might differ from those below, depending on the time you want to write and whether topics have been assigned to other students in the meantime.
-
Identification of persuasiveness effects on reader audience through metaphorical framing in political discourse
This thesis is aimed at dealing with identification of persuasiveness effects in political discourses with the help of metaphors and metaphorical components. Metaphors have been historically used to frame texts in political discourses with the intent to impress upon (persuade) the reader of certain ideologies (left or right; broadly speaking) towards their stances on the the topic of the discourse. We seek to explore how LLMs aid in detection of persuasiveness effects with the information of the metaphors present in the discourses.
Advisor: Meghdut Sengupta
-
Culturally Inconsiderate Models: Teaching LLMs to consider cultural contexts for better Stereotype detection
Recent works on stereotype detection indicates that current Large Language Models (LLMs) are not able to properly predict whether a stereotype is recognized in a specific cultural context. One of the main reasons for this shortcoming is their seemingly inability to consistently consider the cultural context. While prompting in a different language seems to improve this aspect, it remains unclear why that is the case and how to control this behavior better.
Hence, the topic of this thesis is concerned with training LLMs to better consider the relevant cultural context and evaluate its effect on culture-specific stereotype detection. As such, this topic will involve developing text classification models, and setting up a reinforcement learning approach to train a better classification model.
Advisor: Maximilian Spliethöver
-
Generating Feedback for Enthymematic Gaps in Learner Arguments
Learners frequently write arguments that contain enthymemes — logical gaps where a key premise or conclusion is left unstated. While detecting these gaps and reconstructing the missing statement is a crucial first step, simply providing the learner with the "correct" missing sentence (the reconstruction) is not an effective pedagogical approach. Learners will likely benefit more from formative feedback that explains why the gap exists and how to address it. This thesis aims to develop and evaluate a novel NLP approach that goes beyond enthymeme detection and reconstruction to generate constructive, actionable feedback on enthymemes in learner arguments.
Advisor: Maja Stahl
Working on the outlined and similar topics involves dealing with state-of-the-art technologies such as neural transformers, contrastive learning, multitask learning, and/or various others. Most topics target the development and empirical evaluation of NLP methods for specific tasks.
Interested?
Candidates should have very good programming skills (preferably in Python) as well as some experience with machine learning and other AI methods (ideally with NLP). You should be enrolled in one of the computer science programs at Leibniz University Hannover.
In case you are interested, please send a mail to thesis-nlp@ai.uni-hannover.de, including information about the prior knowledge and experience you have:
- What topic are you interested in?
- What relevant courses did you take?
- What experience with AI development and evaluation do you have?
- What other relevant knowledge do you have?
Please note that, due to high demand, ideally let us know a few months in advance if you want to write your thesis with us.
Evaluation
The grading of a thesis is based on a weighted grades for two parts:
- The developed solution to the problem tackled in thesis (45%)
- The written thesis presenting the solution (55%)
The grading of the developed solution takes five criteria into account:
- Difficulty / Complexity. How difficult was it to develop the solution? How much effort was put into it? Is the complexity justified? ...
- Technical quality. Is the design and realization of the solution well-made? Are the experiments systematic and scientifically sound? ...
- Novelty and own ideas. Does the solution have scientific novelty? Have own ideas been developed and realized in the solution? ...
- Impact / Publishability. Does the solution improve the state of the art? Are the results worth publishing? Can they be published as is? ...
- Implementation and data. How easy is it to read and reuse the code? If data has been created, is it well-organized? Are they well-documented? ...
The grading of the written thesis takes six criteria into account:
- Abstract, introduction, and conclusion. Are problem, solution, and results well-introduced? Are the right conclusions made? Is the whole story told? ...
- Background and related work. Are basics well-described and relevant? Is the connection to the thesis clear? Is the state of the art well-discussed? ...
- Approaches and data. Is the presentation of the developed approaches and data clear, complete, and on the right technical level? ...
- Experiments, evaluation, and discussion. Are the experiments described systematically? Are the results clearly presented and correctly interpreted? ...
- Form, layout, and style. Is the structure convincing? Is the writing clear and error-free? Do tables and figures support it? Are citations correct? ...
- Scientific quality. Does the thesis adhere to scientific standards? Does the presentation follow community principles? …
Past Theses (at Leibniz University Hannover)
2026
- Semantics-Guided LLM Prompting for Metaphor Paraphrasing. Given Halim, Bachelor's thesis, 2026, LUH
- Personalized Analogy-Based Explanation Generation with LLMs by Modeling Explainee’s Knowledge. Luis Melzer, Bachelor's thesis, 2026, LUH
- Towards Constructive Discourse: Improving Deliberative Argument Quality with Large Language Models. Claudia Bruhn, Master's thesis, 2026, LUH
2025
- Learning to Score the Group Specificity of Explanations using Contrastive Embedding Spaces. Jannes Lötfering, Bachelor's thesis, 2025, LUH
- Exploring the Impact of Analogical Reasoning on Scientific News Article Generation with LLMs. Julian Vögel, Bachelor's thesis, 2025, LUH
- Aligning Reasoning Large Language Models for Essay Feedback Generation, Erik Vogel, Master's thesis, 2025, LUH
- What Makes an Argument In/-Appropriate: Linguistic Feature Extraction for In/-Appropriate Arguments. Maximilian Olschewski, Bachelor's thesis, 2025, LUH
- Developing and Evaluating an Approach for Identifying Hidden Aspects in Metaphors. Thorben Braun, Bachelor's thesis, 2025, LUH
- Active Learning Supported Data Translation for German Stereotype Classification. Lukas Zain, Master's thesis, 2025, LUH
- Dialect Translation for Fairness in Social Bias Detection using LLM Few-Shot Prompting and Adapter Fine-Tuning. Maximilian Siebenthaler , Master's thesis, 2025, LUH
- Analyzing the Effect of Large Language Model Explanations on Annotator Disagreement. Mark Nagengast-Porro, Master's thesis, 2025, LUH
- Modifying the Attention Mechanism in LLMs for Controlled Essay Feedback Generation. Joshua Heitbreder, Bachelor's thesis, 2025, LUH
- Developing Interpretable Style Vectors to Steer Large Language Models towards Group-Specific Explanation Generation. Janek Prange, Master's thesis, 2025, LUH
- Inferring Natural Language Tasks from Input-Output Pairs using Instruction-Finetuned LLMs. Steffan Wolter, Bachelor's thesis, 2025, LUH
- Analyzing the Impact of Metaphors on Persuasiveness Prediction in News Editorials Using Large Language Models. Hossein Azmoodeh, Master's thesis, 2025, LUH
- Evaluating Advanced VLM Prompting Strategies for the Explanation of Figurative Images and Memes, Julia Köpp, Bachelor's thesis, 2025, LUH
2024
- Augmenting Corpora through Generative Language Model Translation to English Dialect for Enhanced Fairness in Classifier Performance. Alexander Espig, Bachelor's thesis, 2024, LUH
- Preserving Sociodemographic Integrity in Text Data Augmentation. Leon Zalosny, Bachelor's thesis, 2024, LUH
- Guiding Text Revisions Through Explanations, Tim Knebler. Master's thesis, 2024, LUH
- Generating Factual Arguments by Instruction-Fine-Tuning LLMs on Factual Causal Questions. Aryan Shakya, Bachelor's thesis, 2024, LUH
- Approaches to Generate Hidden Aspects in Metaphors, Yosef Ian Kurniadi. Bachelor's thesis, 2024, LUH
- Using Dialectics to Strengthen the Idea Development of Large Language Models. Muaaz Murad Agha, Master's thesis, 2024, LUH
- Generating Feedback for Student Essays via Prompting Large Language Models. Leon Biermann, Bachelor's thesis, 2024, LUH
- Prompting Instruction-Tuned Large Language Models to Identify Social Bias. Steffen Weßbecher, Bachelor's thesis, 2024, LUH
- Developing an Explanation Dialogue System - via Planning and Realization. Yaman Rajab Tabab, Bachelor's thesis, 2024, LUH
- Analyzing the Impact of Context on Downstream Argument Assessment Tasks. Lasse Gellrich, Master's thesis, 2024, LUH
Past Theses (at Paderborn University)
2023
- Evaluating Data-Driven Approaches to Improve Word Lists for Measuring Social Bias in Word Embeddings. Master's thesis, Vinay Kaundinya Ronur Prakash, 2023, UPB.
- Audience Aware Counterargument Generation. Master's thesis. Mahammad Namazov, 2023, UPB.
- Improving Learners’ Arguments by Detecting and Generating Missing Argument Components. Master's thesis, Nick Düsterhus, 2023, UPB.
- Gender-inclusive Coreference Resolution using Pronoun Preference. Master's thesis, Jan-Luca Hansel, 2023, UPB.
2022
- Dialect-aware Social Bias Detection using Ensemble and Multi-Task Learning. Master's thesis, Sai Nikhil Menon, 2022, UPB.
- Counter Argument Generation Using a Knowledge Graph. Master's thesis, Indranil Ghosh, 2022, UPB.
- Domain-aware Text Professionalization using Sequence-to-Sequence Neural Networks. Bachelor's thesis, Juela Palushi, 2022, UPB.
- Detection and Mitigation of Subjective Bias in Argumentative Text. Master's thesis, Sambit Mallick, 2022, UPB.
- Cross-domain analysis of argument quality and its connection to offensive language. Bachelor's thesis, Patrick Bollmann, 2022, UPB.
- Cross-domain Aspect-based Sentiment Analysis with Multimodal Sources. Master's thesis, Pavan Kumar Sheshanarayana, 2022, UPB.
- Comparative Evaluation of Automatic Summarization Techniques for German Court Decision Documents. Master's thesis, Josua Köhler, 2022, UPB.
- Computational Analysis of Cultural Differences in Learner Argumentation.Master's thesis, Garima Mudgal, 2022, UPB.
- Propaganda Technique Detection Using Connotation Frames. Master's thesis, Vinaykumar Budanurmath, 2022, UPB.
- Contrastive Argument Summarization using Supervised and Unsupervised Learning. Master's thesis, Jonas Rieskamp, 2022, UPB.
2021
- Mitigation of Gender Bias in Text using Unsupervised Controllable Rewriting. Master's thesis, Maja Brinkmann, 2021, UPB. **Best Master's Thesis Award at Paderborn University**
- Assessing Stereotypical Social Biases in Text Sequences using Language. Master's thesis, Meher Vivek Dheram, 2021, UPB.
- Modeling Context and Argumentativeness of Sentences in Argument Snippet Generation. Master's thesis, Harsh Shah, 2021, UPB.
- Political Speaker Transfer: Learning to Generate Text in the Styles of Barack Obama and Donald Trump. Master's thesis, Jonas Bülling, 2021, UPB.
- Quantifying Social Biases in News Articles with Word Embeddings. Bachelor's thesis, Maximilian Keiff, 2021, UPB.
- Computational Text Professionalization using Neural Sequence-to-Sequence Models. Master's thesis, Avishek Mishra, 2021, UPB.
- Assessing the Argument Quality of Persuasive Essays using Neural ext Generation. Master's thesis, Timon Gurcke, 2021, UPB.
2020
- Automatic Conclusion Generation using Neural Networks. Bachelor's thesis, Torben Zöllner, 2020, UPB.
- Computational Analysis of Metaphors based on Word Embeddings. Bachelor's thesis, Simon Krenzler, 2020, UPB.
- Semi-supervised Cleansing of Web-based Argument Corpora. Bachelor's thesis, Jonas Dorsch, 2020, BUW.
- Countering Natural Language Arguments using Neural Sequence-to-Sequence Generation. Master's thesis, Arkajit Dhar, 2020, UPB.
2019
- Snippet Generation for Argument Search. Bachelor's thesis, Nick Düsterhus, 2019, UPB.
- Argument Quality Assessment in Natural Language using Machine Learning — bachelor's thesis, Till Werner, 2019, UPB.
- Stance Classification in Argument Search. Master's thesis, Philipp Heinisch, 2019, UPB.
- Towards a Large-scale Causality Graph. Bachelor's thesis, Yan Scholten, 2019, UPB.
Past Theses (at Bauhaus Universtität Weimar & Paderborn University)
2017
- Cross-Domain Mining of Argumentation Strategies using Natural Language Processing. Master's thesis, 2017, BUW.
- Mining Relevant Arguments at Web Scale. Master's thesis, 2017, BUW.
2016
- Identifying Controversial Topics in Large-Scale Social Media Data. Master's thesis, 2016, BUW.
2013
- Efficiency and Effectiveness of Multi-Stage Machine Learning Algorithms for Text Quality Assessment. Master's thesis, 2013, UPB.
2012
- An Expert System for the Automatic Construction of Information Extraction Pipelines. Master's thesis, 2012, UPB.
- Efficiency and Effectiveness of Text Classification in Information Extraction Pipelines. Master's thesis, 2012, UPB.
- Efficient Information Extraction for Creating Use Case Diagrams from Text. Master's thesis, 2012, UPB.
- Heuristic Search for the Run-time Optimization of Information Extraction Pipelines. Master's thesis, 2012, UPB.
2011
- Aggregation and Visualization of Market Forecasts. Bachelor's thesis, 2011, UPB.
- Branch Categorization based on Statistical Analysis of Information Retrieval Results. Bachelor's thesis 2011, UPB.
2009
- Evaluation of Cooperative Robot Motion Strategies in Simbad. Bachelor's thesis, 2009, UPB.
LUH: Leibniz University Hannover, UPB: Paderborn University, BUW: Bauhaus-Universität Weimar
