Papers by Diego Frassinelli
Figurative Language Processing: A Linguistically Informed Feature Analysis of the Behavior of Language Models and Humans (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent years have witnessed a growing interest in investigating what Transformer-based language models (TLMs) actually learn from training data. |
| Approach: | They propose to use a black-box TLM and two intrinsically transparent white-box models to investigate the performance of figurative language models on sarcasm, similes, idioms, and metaphors. |
| Outcome: | The proposed models perform better than other models on figurative language classification tasks. |
To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have remarkable performance in a variety of tasks due to factual knowledge accumulated during pre-training. |
| Approach: | They propose an evaluation protocol that disentangles knowing from applying knowledge and test state-of-the-art LLMs on 49 ambiguous entities. |
| Outcome: | The proposed evaluation protocol disentangles knowing from applying knowledge and tests state-of-the-art LLMs on 49 ambiguous entities. |
Disentangling Subjectivity and Uncertainty for Hate Speech Annotation and Modeling using Gaze (2025.emnlp-main)
Copied to clipboard
Özge Alacam, Sanne Hoeken, Andreas Säuberli, Hannes Gröner, Diego Frassinelli, Sina Zarrieß, Barbara Plank
| Challenge: | Variation is inherent in opinion-based annotation tasks like sentiment or hate speech analysis. |
| Approach: | They propose to use annotators' confidence ratings to disentangle subjective variation from uncertainty without relying on specific features present in the data. |
| Outcome: | The proposed approach shows that human gaze patterns offer valuable indicators of subjective evaluation and uncertainty. |
AbsVis – Benchmarking How Humans and Vision-Language Models “See” Abstract Concepts in Images (2025.emnlp-main)
Copied to clipboard
| Challenge: | Abstract concepts like mercy and peace lack clear visual grounding, and therefore challenge humans and models to provide suitable image representations. |
| Approach: | They propose a dataset of 675 images annotated with 14,175 concept–explanation attributions from humans and two Vision-Language Models where each concept is accompanied by a textual explanation. |
| Outcome: | The proposed dataset compares human and VLM attributions in terms of diversity, abstractness, and alignment, and shows that overlapping concepts are most preferred. |
GerMedIQ: A Resource for Simulated and Synthesized Anamnesis Interview Responses in German (2025.acl-srw)
Copied to clipboard
Justin Hofenbitzer, Sebastian Schöning, Belle Sebastian, Jacqueline Lammert, Luise Modersohn, Martin Boeker, Diego Frassinelli
| Challenge: | Text corpora in non-English clinical contexts is scarce due to privacy restrictions and restricted access to secure environments. |
| Approach: | They propose to use Large Language Models to generate synthetic data using a German medical interview questions corpus. |
| Outcome: | The proposed dataset generates comparable responses to human-generated questions. |
Unveiling the mystery of visual attributes of concrete and abstract concepts: Variability, nearest neighbors, and challenging categories (2024.emnlp-main)
Copied to clipboard
| Challenge: | a recent study examines the visual representation of concrete concepts using images from Bing and YFCC. |
| Approach: | They examine the variability in visual representations by using images of concrete and abstract concepts from Bing and YFCC. |
| Outcome: | The proposed model can distinguish between concrete and abstract concepts using basic visual features, the authors show . their model outperforms other models in the nearest neighbor analysis, but it is more complex and requires more visual features . |
A Couch Potato is not a Potato on a Couch: Prompting Strategies, Image Generation, and Compositionality Prediction for Noun Compounds (2025.findings-acl)
Copied to clipboard
| Challenge: | a new method to predict the compositionality of English noun compounds is proposed . |
| Approach: | They propose a visual modality and vision transformers to predict the compositionality of English noun compounds. |
| Outcome: | The proposed method compared with a state-of-the-art text-based approach reveals complementary contributions regarding features and degrees of abstractness in English noun compounds. |
Concreteness vs. Abstractness: A Selectional Preference Perspective (2022.aacl-srw)
Copied to clipboard
| Challenge: | Using a collection of 5,438 nouns and 1,275 verbs, we exploit selectional preferences as a salient characteristic in classifying abstract vs. concrete words. |
| Approach: | They propose to use selectional preferences as a criterion to distinguish between concrete and abstract concepts and words. |
| Outcome: | The proposed method achieves an f1-score of 0.84 for nouns and 0.71 for verbs in classification and Spearman’s correlation of 0.86 for nonoms and 0.59% for verb. |
GRIT: A Dataset of Group Reference Recognition in Italian (2024.lrec-main)
Copied to clipboard
| Challenge: | a task of automatically recognizing group references has not yet gained much attention within NLP. |
| Approach: | They propose a large-scale dataset for automatic group reference recognition in italian . they verify the validity of the task using a fine-tuned BERT model . |
| Outcome: | The proposed dataset proves that it can be applied to political text analysis and social media analysis. |
Make Every Letter Count: Building Dialect Variation Dictionaries from Monolingual Corpora (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Dialects exhibit a substantial degree of variation due to the lack of a standard orthography . however, the ability of Large Language Models (LLMs) to process dialects remains understudied . |
| Approach: | They propose a framework for creating dialect variation dictionaries from monolingual data . they use a dataset to examine how well LLMs can judge Bavarian terms as dialect translations . |
| Outcome: | The proposed framework can judge dialects as dialect translations, inflected variants or unrelated forms of a given German lemma. |
Linguistic Features in German BERT: The Role of Morphology, Syntax, and Semantics in Multi-Class Text Classification (2025.naacl-srw)
Copied to clipboard
| Challenge: | a monolingual German BERT model is used for semantic classification of newspaper articles . linguistic features identified in English affect classification in German, but suggest important language- and task-specific features as well. |
| Approach: | They examine a monolingual German BERT model using a semantic classification task on newspaper articles. |
| Outcome: | The proposed model uses the TüBa-D/Z corpus, a resource with gold-standard annotations for linguistic features. |
Controlling Reading Ease with Gaze-Guided Text Generation (2026.eacl-long)
Copied to clipboard
| Challenge: | Using a gaze-based model, we generate texts with controllable reading ease. |
| Approach: | They propose a method that predicts gaze patterns to steer language model outputs towards eliciting certain reading behaviors by predicting eye-tracking measures. |
| Outcome: | The proposed method generates texts with controllable reading ease using eye-tracking with native and non-native speakers of English. |
Generalizable Sarcasm Detection is Just Around the Corner, of Course! (2024.naacl-long)
Copied to clipboard
| Challenge: | sarcasm can be used to hurt, criticize, or deride but also to be mocking, humorous, or to bond. |
| Approach: | They tested the robustness of sarcasm detection models by fine-tuning their behavior on four sarkasmatic datasets . they found that models performed better when fine- tuned with third-party labels than with author labels. |
| Outcome: | The proposed models performed better when fine-tuned with third-party labels than with author labels on the same dataset and across different datasets. |