Gerhard Weikum
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Gerhard Weikum has a total of 199 co-authors. Here are the top co-authors by number of shared publications:
- Simon Razniewski
ScaDS.AI & TU Dresden, Dresden, Germany
11 shared publications - Rishiraj Saha Roy
Fraunhofer Institute for Integrated Circuits IIS Am Wolfsmantel 33 91058 Erlangen Germany
10 shared publications - Philipp Christmann
CISPA Helmholtz Center for Information Security, Saarbruecken, Germany
7 shared publications - Simon Razniewski
Max Planck Institute for Informatics Saarland Informatics Campus 66123 Saarbrücken Germany
7 shared publications Gottfried Vossen
University of Munster, Germany
6 shared publicationsSimon Razniewski
Max Planck Institute for Informatics
6 shared publications
Latest Publications
- Open Access
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1100-1106
PerQA: A Benchmark for Temporally Sensitive Questions on Heterogeneous Personal Data
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1100-1106
Open AccessPerQA: A Benchmark for Temporally Sensitive Questions on Heterogeneous Personal Data
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6693-6697
L3X: Long Object List Extraction from Long Documents
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6693-6697
Open AccessL3X: Long Object List Extraction from Long Documents
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6619-6623
The ReQAP System for Question Answering over Personal Information
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6619-6623
Open AccessThe ReQAP System for Question Answering over Personal Information
- Open Access
Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data
Question answering over mixed sources, like text and tables, has been advanced by verbalizing all contents and encoding it with a language model. A prominent case of such heterogeneous data is personal information: user devices log vast amounts of data every day, such as calendar entries, workout statistics, shopping records, streaming history, and more. Information needs range from simple look-ups to queries of analytical nature. The challenge is to provide humans with convenient access with small footprint, so that all personal data stays on the user devices. We present ReQAP, a novel method that creates an executable operator tree for a given question, via recursive decomposition. Operators are designed to enable seamless integration of structured and unstructured sources, and the execution of the operator tree yields a traceable answer. We further release the PerQA benchmark, with persona-based data and questions, covering a diverse spectrum of realistic user needs.
Open AccessRecursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data
Question answering over mixed sources, like text and tables, has been advanced by verbalizing all contents and encoding it with a language model. A prominent case of such heterogeneous data is personal information: user devices log vast amounts of data every day, such as calendar entries, workout statistics, shopping records, streaming history, and more. Information needs range from simple look-ups to queries of analytical nature. The challenge is to provide humans with convenient access with small footprint, so that all personal data stays on the user devices. We present ReQAP, a novel method that creates an executable operator tree for a given question, via recursive decomposition. Operators are designed to enable seamless integration of structured and unstructured sources, and the execution of the operator tree yields a traceable answer. We further release the PerQA benchmark, with persona-based data and questions, covering a diverse spectrum of realistic user needs.
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1053-1057
Preference-based Learning with Retrieval Augmented Generation for Conversational Question Answering
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1053-1057
Open AccessPreference-based Learning with Retrieval Augmented Generation for Conversational Question Answering
- 4 April 2025
- Published by Springer Nature
- p. 360-375
CUP: A Framework for Resource-Efficient Review-Based Recommenders
- 4 April 2025
- Published by Springer Nature
- p. 360-375
CUP: A Framework for Resource-Efficient Review-Based Recommenders
- 4 April 2025
- Published by Springer Nature
- p. 275-283
Efficient and Effective Conversational Search with Tail Entity Selection
- 4 April 2025
- Published by Springer Nature
- p. 275-283
Efficient and Effective Conversational Search with Tail Entity Selection
- Open Access
Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions
Much has been discussed about how Large Language Models, Knowledge Graphs and Search Engines can be combined in a synergistic manner. A dimension largely absent from current academic discourse is the user perspective. In particular, there remain many open questions regarding how best to address the diverse information needs of users, incorporating varying facets and levels of difficulty. This paper introduces a taxonomy of user information needs, which guides us to study the pros, cons and possible synergies of Large Language Models, Knowledge Graphs and Search Engines. From this study, we derive a roadmap for future research.
Open AccessLarge Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions
Much has been discussed about how Large Language Models, Knowledge Graphs and Search Engines can be combined in a synergistic manner. A dimension largely absent from current academic discourse is the user perspective. In particular, there remain many open questions regarding how best to address the diverse information needs of users, incorporating varying facets and levels of difficulty. This paper introduces a taxonomy of user information needs, which guides us to study the pros, cons and possible synergies of Large Language Models, Knowledge Graphs and Search Engines. From this study, we derive a roadmap for future research.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18269-18288
Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data
Philipp Christmann, Gerhard Weikum. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18269-18288
Open AccessRecursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data
Philipp Christmann, Gerhard Weikum. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
RAG-based Question Answering over Heterogeneous Data and Text
This article presents the QUASAR system for question answering over unstructured text, structured tables, and knowledge graphs, with unified treatment of all sources. The system adopts a RAG-based architecture, with a pipeline of evidence retrieval followed by answer generation, with the latter powered by a moderate-sized language model. Additionally and uniquely, QUASAR has components for question understanding, to derive crisper input for evidence retrieval, and for re-ranking and filtering the retrieved evidence before feeding the most informative pieces into the answer generation. Experiments with three different benchmarks demonstrate the high answering quality of our approach, being on par with or better than large GPT models, while keeping the computational cost and energy consumption orders of magnitude lower.
Open AccessRAG-based Question Answering over Heterogeneous Data and Text
This article presents the QUASAR system for question answering over unstructured text, structured tables, and knowledge graphs, with unified treatment of all sources. The system adopts a RAG-based architecture, with a pipeline of evidence retrieval followed by answer generation, with the latter powered by a moderate-sized language model. Additionally and uniquely, QUASAR has components for question understanding, to derive crisper input for evidence retrieval, and for re-ranking and filtering the retrieved evidence before feeding the most informative pieces into the answer generation. Experiments with three different benchmarks demonstrate the high answering quality of our approach, being on par with or better than large GPT models, while keeping the computational cost and energy consumption orders of magnitude lower.