Seminar "Search & Synthesis: Information Retrieval meets Large Language Models"

Seminar Details

Lecturer: Prof. Dr. Wolf-Tilo Balke

Supervising Staff: Niklas Kiehne

Degree Programs: Master (Computer Science, Business Informatics, IST, Data Science)

Spoken Language: German

Credits: 5

Examination Requirements: Attendance in all sessions, Presentation & Discussion

Weekly Meetings: Wednesdays, 9:45am in Room IZ251

Kick-Off: 09.04.2025

The Seminar

Our seminars always focus on presentation skills: instead of requiring a written paper, we ask you to develop a captivating and authentic presentation. To prepare you for this, we will spend the first few weeks exploring how to give a good and engaging presentation. Through analyzing various talks, we will discover together what makes a great presentation, and later work on your presentation techniques through practical exercises. Each seminar presentation will be delivered in front of the entire group and followed by an in-depth discussion. This seminar offers you one of the last opportunities before entering the professional world to receive honest feedback on your presentation style and performance. Take advantage of it! If you're interested in learning how to give a convincing presentation and are open to honest feedback, this seminar is the right place for you.

Seminar Topics

Now in the order of presenting! Presentations start 28.05, one topic per week, including excursion week.

1. (28.05) Intro to RAG + Query Expansion: Help retrievers with additional information 
   • Liang Wang, Nan Yang, and Furu Wei. 2023. Query2doc: Query Expansion with Large Language Models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9414–9423, Singapore. Association for Computational Linguistics.
   • Dai, Zhuyun, et al. "Promptagator: Few-shot Dense Retrieval From 8 Examples." The Eleventh International Conference on Learning Representations.
2. (04.06) RAG with Knowledge Graphs:

   • de Jong, Michiel, et al. "Mention Memory: incorporating textual knowledge into Transformers through entity mention attention." International Conference on Learning Representations.

   • Sun, Jiashuo, et al. "Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph." The Twelfth International Conference on Learning Representations.

3. (11.06) Query based RAG for Knowledge Base Question Answering
   • Ye Liu, Semih Yavuz, Rui Meng, Dragomir Radev, Caiming Xiong, and Yingbo Zhou. 2022. Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8858–8869, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
   • Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, and Caiming Xiong. 2022. RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6032–6043, Dublin, Ireland. Association for Computational Linguistics.

   • Yu, Donghan, et al. "DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases." The Eleventh International Conference on Learning Representations. 2022.

4. (18.06) RAG for longtail knowledge: Do LLMs know their limits?
   • Kandpal, Nikhil, et al. "Large language models struggle to learn long-tail knowledge." International Conference on Machine Learning. PMLR, 2023.
   • Ruiyang Ren, Yuhao Wang, Yingqi Qu, Wayne Xin Zhao, Jing Liu, Hua Wu, Ji-Rong Wen, and Haifeng Wang. 2025. Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3697–3715, Abu Dhabi, UAE. Association for Computational Linguistics.
   • Zhengbao Jiang, Jun Araki, Haibo Ding, and Graham Neubig. 2021. How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering. Transactions of the Association for Computational Linguistics, 9:962–977.
5. (25.06) Latent Representation RAG: Scaling up input

   • Borgeaud, Sebastian, et al. "Improving language models by retrieving from trillions of tokens." International conference on machine learning. PMLR, 2022.

   • Bertsch, Amanda, et al. "Unlimiformer: Long-range transformers with unlimited length input." Advances in Neural Information Processing Systems 36 (2024).

6. (02.07) RAG + Action Plans:
   • Yao, Shunyu, et al. "ReAct: Synergizing Reasoning and Acting in Language Models." International Conference on Learning Representations (ICLR). 2023.
   • Asai, Akari, et al. "Self-rag: Learning to retrieve, generate, and critique through self-reflection." The Twelfth International Conference on Learning Representations. 2023.
7. (09.07) Speculative-RAG: Speed up LLM generation with retrieved texts:
   • Zhenyu He, Zexuan Zhong, Tianle Cai, Jason Lee, and Di He. 2024. REST: Retrieval-Based Speculative Decoding. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1582–1595, Mexico City, Mexico. Association for Computational Linguistics.
   • Lan, Tian, et al. "Copy is All You Need." The Eleventh International Conference on Learning Representations. 2022.
   • Cao, Bowen, et al. "Retrieval is Accurate Generation." The Twelfth International Conference on Learning Representations.