Research Areas

You can find the complete list of articles on my Google Scholar or DBLP profiles.

Experience in reviewing or organizing workshops, challenges, special issue, conferences, journals

Experience in supervision, open research topics

Research Topics & Publications

Large Language Models and Dialogue

I study the evaluation and grounding of LLMs in interactive and multimodal settings, with a focus on behavioral benchmarking, reasoning costs, and grounding in conversation.

• Hakimov, S., Bernard, R., Leiber, T., Osswald, K., Richert, K., Yang, R., Bernardi, R., and Schlangen, D. (2026). The Price of Thought: A Multilingual Analysis of Reasoning, Performance, and Cost of Negotiation in Large Language Models. EACL 2026
  PDF
• Yang, J., Feldhus, N., Mohtaj, S., Hennig, L., Wang, Q., Metheniti, E., Hakimov, S., Jakob, C., Solopova, V., Rieck, K., Schlangen, D., Möller, S., and Schmitt, V. (2026). Order in the Evaluation Court: A Critical Analysis of NLG Evaluation Trends.
  PDF
• Hakimov, S., Abdullayeva, Y., Koshti, K., Schmidt, A., Weiser, Y., Beyer, A., and Schlangen, D. (2025). Using Game Play to Investigate Multimodal and Conversational Grounding in Large Multimodal Models. COLING 2025
  PDF
• Chalamalasetti, K., Götze, J., Hakimov, S., Madureira, B., Sadler, P., and Schlangen, D. (2023). clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents. EMNLP 2023
  PDF
• Hakimov, S., and Schlangen, D. (2023). Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks. Findings of ACL 2023
  PDF

Multimodal Understanding and News Analytics

My multimodal work focuses on image-text reasoning, sentiment and geolocation in news, and robust multimodal modeling for social media and news streams.

• Cheema, G.S., Hakimov, S., Müller-Budack, E., Otto, C., Bateman, J., and Ewerth, R. (2023). Understanding Image-Text Relations and News Values for Multimodal News Analysis. Frontiers in Artificial Intelligence
  PDF
• Tahmasebzadeh, G., Hakimov, S., Ewerth, R., and Müller-Budack, E. (2023). Multimodal Geolocation Estimation of News Photos. ECIR 2023
  PDF
• Tahmasebzadeh, G., Hakimov, S., Ewerth, R., and Müller-Budack, E. (2023). MM-Locate-News: Multimodal Focus Location Estimation in News. MMM 2023
  PDF
• Thakkar, G., Hakimov, S., and Tadic, M. (2024). M2SA: Multimodal and Multilingual Model for Sentiment Analysis of Tweets. LREC-COLING 2024
  PDF
• Cheema, G.S., Hakimov, S., Müller-Budack, E., and Ewerth, R. (2021). A Fair and Comprehensive Comparison of Multimodal Tweet Sentiment Analysis Methods. MMPT 2021
  PDF

Misinformation and Harmful Content Detection

This line of work develops models and resources for detecting misinformation, claims, and harmful content in multimodal social media and news.

• Tahmasebi, S., Hakimov, S., Ewerth, R., and Müller-Budack, E. (2023). Improving Generalization for Multimodal Fake News Detection. ICMR 2023
  PDF
• Hakimov, S., Cheema, G.S., and Ewerth, R. (2022). TIB-VA at SemEval-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous Memes. SemEval 2022
  PDF
• Cheema, G.S., Hakimov, S., Müller-Budack, E., and Ewerth, R. (2021). On the Role of Images for Analyzing Claims in Social Media. WWW Workshop (CLEOPATRA 2021)
  PDF
• Cheema, G.S., Hakimov, S., and Ewerth, R. (2020). Check_square at CheckThat! 2020: Claim Detection in Social Media via Fusion of Transformer and Syntactic Features. CLEF 2020
  PDF

Semantic Parsing and Knowledge Graph QA

I work on semantic parsing, knowledge base question answering, and structured meaning representations for multilingual settings.

• Hakimov, S. (2019). Learning Multilingual Semantic Parsers for Question Answering over Linked Data. PhD Dissertation
  PDF
• Hakimov, S., Jebbara, S., and Cimiano, P. (2019). Evaluating Architectural Choices for Deep Learning Approaches for Question Answering over Knowledge Bases. ICSC 2019
  PDF
• Hakimov, S., Jebbara, S., and Cimiano, P. (2017). AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data. ISWC 2017
  PDF
• Hakimov, S., Unger, C., Walter, S., and Cimiano, P. (2015). Applying Semantic Parsing to Question Answering over Linked Data: Addressing the Lexical Gap. NLDB 2015
  PDF

Video Summarization

I build multimodal approaches for summarizing long-form educational and lecture videos, balancing informativeness and compactness.

• Ghauri, J.A., Hakimov, S., and Ewerth, R. (2021). Supervised Video Summarization via Multiple Feature Sets with Parallel Attention. ICME 2021
  PDF
• Ghauri, J.A., Hakimov, S., and Ewerth, R. (2020). Classification of Important Segments in Educational Videos using Multimodal Features. CIKM Workshops 2020
  PDF

Event-Centric Analytics

This work focuses on event understanding and classification across multimodal and multilingual sources.

• Müller-Budack, E., Springstein, M., Hakimov, S., Mrutzek, K., and Ewerth, R. (2021). Ontology-driven Event Type Classification in Images. WACV 2021
  PDF
• Demidova, E., Hakimov, S., Winters, J., and Tadic, M. (2020). Proceedings of the 1st International Workshop on Cross-lingual Event-centric Open Analytics (CLEOPATRA 2020). ESWC 2020 Workshops
  PDF