Papers by Fabian David Schmidt
ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models exhibit more language confusion as they become multilingual . authors propose a lightweight approach for reducing language confusion based on language-specific steering vectors . |
| Approach: | They propose a lightweight approach to reduce language confusion by using language-specific steering vectors. |
| Outcome: | The proposed approach reduces language confusion in large language models . it leverages language-specific steering vectors for effective LLM steering . |
SEAGLE: A Platform for Comparative Evaluation of Semantic Encoders for Information Retrieval (D19-3)
Copied to clipboard
| Challenge: | Existing semantic text encoding models are limited in coverage and few attempts to empirically compare them on IR tasks have been made. |
| Approach: | They propose to implement word embedding aggregators and pretrained semantic encoders and to allow for their comparative evaluation on arbitrary IR collections. |
| Outcome: | The proposed model can be exploited via an easy-to-use web interface and its modular backend (micro-service architecture) can easily be extended with additional semantic search models. |
BABELEDITS: A Benchmark and a Modular Approach for Robust Cross-lingual Knowledge Editing of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for cross-lingual knowledge editing are limited in their effectiveness and robustness. |
| Approach: | They propose a new CKE benchmark that accounts for the rich variety of entity aliases within and across languages. |
| Outcome: | The proposed method is more effective than state-of-the-art methods and robust against model collapse when subjected to multiple edits. |
Don’t Stop Fine-Tuning: On Training Regimes for Few-Shot Cross-Lingual Transfer with Multilingual Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work highlights the fallacies of zero-shot cross-lingual transfer with large multilingual models. |
| Approach: | They propose to replace sequential fine-tuning with joint fine-uning on source and target language instances. |
| Outcome: | The proposed techniques yield improved and more stable FS-XLT across the board. |
SLICER: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity Recognition (2022.emnlp-main)
Copied to clipboard
| Challenge: | Large multilingual models fail to successfully transfer to low-resource languages for zero-shot cross-lingual transfer . sliced fine-tuning for named entity recognition (SLICER) forces stronger token contextualization in the Transformer. |
| Approach: | They propose a simple yet highly effective approach for improving zero-shot cross-lingual transfer for named entity recognition to low-resource languages. |
| Outcome: | The proposed approach reduces decontextualization of token representations and classifiers . it yields consistent transfer gains for low-resource languages, the authors show . |
MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing multilingual vision-language (VL) benchmarks typically only cover a handful of languages, underscoring the need for evaluation data for low-resource languages. |
| Approach: | They propose a multilingual vision-language benchmark that evaluates cross-modal and text-only topical matching across 205 languages. |
| Outcome: | The proposed model performs better in cross-modal and text-only topical matching in lower-resource languages than the most multilingual benchmarks. |
One For All & All For One: Bypassing Hyperparameter Tuning with Model Averaging for Cross-Lingual Transfer (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for zero-shot cross-lingual transfer are unreliable due to the lack of pretraining data. |
| Approach: | They propose to accumulatively average model snapshots from different runs into a single model. |
| Outcome: | The proposed protocol decouples performance maximization from hyperparameter tuning. |
On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented Cultures (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) should be able to provide accurate information irrespective of the measurement system at hand . |
| Approach: | They use newly compiled datasets to test if this is true for seven open-source LLMs. |
| Outcome: | The proposed model can provide accurate information regardless of the measurement system at hand. |
Free Lunch: Robust Cross-Lingual Transfer via Model Checkpoint Averaging (2023.acl-long)
Copied to clipboard
| Challenge: | Massively multilingual language models have shown strong performance in zero-shot (ZS-XLT) and few-shot cross-lingual transfer setups where models are fine-tuned on task data in a source language are transferred without any or with only a few annotated instances to the target language(s). |
| Approach: | They propose a method that averages different checkpoints during task fine-tuning to improve model robustness. |
| Outcome: | The proposed method overestimates model performance in cross-lingual transfer setups where models are evaluated at checkpoints that generalize best to validation instances in the target languages. |