I am a second-year ELLIS PhD Student at the University of Munich and the University of Cambridge, advised by Hinrich Schütze and Anna Korhonen. My research interests include few-shot and unsupervised learning in NLP, data-centric methods for effective large language models, and computational social science.

Prior to starting my PhD, I received my BSc and MSc in Computer Engineering from Bogazici University, Istanbul, advised by Arzucan Ozgur. I worked as an applied science intern at Amazon Books in Madrid, focusing on structured prediction from long-text documents. Recently, I interned at Google in Mountain View, working on attribution and counterfactuality in large language models.

News

June 2023: I will be in Mountain View for 3 months as a research intern at Google, focusing on attribution and counterfactuality in large language models.

May 2023: New preprint: Language-Agnostic Bias Detection in Language Models

April 2023: New preprints:

• LongForm: Optimizing Instruction Tuning for Long Text Generation with Corpus Extraction (Talk at Munich NLP)
• Sociocultural knowledge is needed for selection of shots in hate speech detection tasks

December 2022: I will attend EMNLP 2022 in Abu Dhabi. Ping me if you would like to chat!

November 2022: New preprint: MEAL: Stable and Active Learning for Few-Shot Prompting

October 2022: The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative is accepted at EMNLP 2022.
📃 New preprint: SilverAlign: MT-Based Silver Data Algorithm For Evaluating Word Alignment

September 2022: I attended ELLIS Doctoral Symposium in Alicante and presented our work on language-agnostic racial bias detection in LMs.

Selected Publications

1. Köksal, A.; Schick, T.; Korhonen, A.; Schütze, H.; LongForm: Optimizing Instruction Tuning for Long Text Generation with Corpus Extraction. arXiv preprint. 2023.
2. Köksal, A.; Yalcin, O.F.; Akbiyik, A.; Kilavuz, M.T.; Korhonen, A.; Schütze, H.; Language-Agnostic Bias Detection in Language Models. arXiv preprint. 2023.
3. Köksal, A.; Schick, T.; Schütze, H.; MEAL: Stable and Active Learning for Few-Shot Prompting. arXiv preprint. 2022.
4. Weissweiler, L.; Hoffmann, V.; Köksal, A.; Schütze, H.; The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative. EMNLP 2022.
5. Türk, U.; Atmaca, F.; Özateş, Ş.B.; Berk, G.; Bedir, S.T.; Köksal, A.; Öztürk, B.; Güngör, T.; Özgür, A.; Resources for Turkish Dependency Parsing: Introducing the BOUN Treebank and the BoAT Annotation Tool. Language Resources and Evaluation 2022.
6. Huang, Y.; Giledereli, B.; Köksal, A.; Özgür, A.; Ozkirimli, E.; Balancing Methods for Multilabel Text Classification with Long-Tailed Class Distribution. EMNLP 2021.
7. Köksal, A.; Özgür, A.; The RELX Dataset and Matching the Multilingual Blanks for Cross-lingual Relation Classification. Findings of EMNLP 2020.
8. Köksal, A.; Dönmez, H; Özçelik, R.; Ozkirimli, E.; Özgür, A.; Vapur: A Search Engine to Find Related Protein – Compound Pairs in COVID-19 Literature. Workshop on NLP for COVID-19 at EMNLP 2020. 🛳 Demo.