Papers by Daniel Hershcovich
Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Using large vision-language models to understand cultural contexts is a critical area of research. |
| Approach: | They conduct a thorough evaluation of multimodal models at different scales, focusing on their alignment with cultural values. |
| Outcome: | The proposed models show that they exhibit sensitivity to cultural values but their performance is highly context-dependent. |
Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is a promising approach for cross-cultural recipe adaptation, but it fails to generate diverse results even when provided with varied contextual inputs. |
| Approach: | They propose a plug-and-play RAG framework that enhances diversity in both retrieval and context organization to generate diverse outputs to accommodate multiple user preferences. |
| Outcome: | The proposed framework achieves Pareto efficiency in terms of diversity and quality of recipe adaptation compared to closed-book LLMs. |
Beyond Demographics: Enhancing Cultural Value Survey Simulation with Multi-Stage Personality-Driven Cognitive Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Introducing **MARK**, a framework for cultural value survey simulation . based on type dynamics theory, it improves accuracy and interpretation of models . |
| Approach: | They propose a framework that integrates psychological theory into cultural value survey simulations. |
| Outcome: | The proposed framework outperforms baseline models on the World Values Survey by 10% accuracy and reduces divergence between model predictions and human preferences. |
Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge (2025.naacl-long)
Copied to clipboard
Li Zhou, Taelin Karidi, Wanlong Liu, Nicolas Garneau, Yong Cao, Wenyu Chen, Haizhou Li, Daniel Hershcovich
| Challenge: | Recent studies have highlighted the presence of cultural biases in Large Language Models (LLMs), yet lack a robust methodology to dissect these phenomena comprehensively. |
| Approach: | They propose a multilingual dataset centered on food-related cultural facts and variations in food practices. |
| Outcome: | The proposed model incorporates cultural context significantly and improves its ability to access cultural knowledge. |
Compositional Generalization in Multilingual Semantic Parsing over Wikidata (2022.tacl-1)
Copied to clipboard
| Challenge: | Semantic parsers are mostly designed for and evaluated on English resources, such as CFQ. |
| Approach: | They propose a method for creating a multilingual, parallel question-query dataset . they analyze compositional generalization of parsers in Hebrew, Kannada, Chinese, and English . |
| Outcome: | The proposed method analyzes compositional generalization of parsers in Hebrew, Kannada, Chinese, and English. |
Cross-lingual Semantic Representation for NLP with UCCA (2020.coling-tutorials)
Copied to clipboard
| Challenge: | introductory tutorial to UCCA, a symbolic meaning representation for semantic representations. |
| Approach: | This tutorial introduces UCCA, a cross-linguistically applicable framework for semantic representation . it will provide a detailed introduction to the UCca annotation guidelines, design philosophy and available resources . |
| Outcome: | The tutorial will provide a detailed introduction to the UCCA framework and compare it to other meaning representations. |
The Language of Legal and Illegal Activity on the Darknet (P19-1)
Copied to clipboard
| Challenge: | a study of the characteristics of text in the Darknet shows that it has legal and illegal content. |
| Approach: | They compare texts for selling legal and illegal drugs to a control condition . they find several distinguishing features between legal and illicit texts . |
| Outcome: | The authors compare legal and illegal texts to a clear net website with similar content as a control condition. |
Bridging Cultures in the Kitchen: A Framework and Benchmark for Cross-Cultural Recipe Retrieval (2024.emnlp-main)
Copied to clipboard
| Challenge: | Adapting recipes to cultural differences presents significant importance and challenges . bridging cultural differences is a challenge, but IR can help. |
| Approach: | They propose a framework that preserves the original recipe and its cultural appropriateness for the target culture. |
| Outcome: | The proposed framework preserves the original recipe and its cultural appropriateness for the target culture while maintaining relevance to the original. |
Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation (2026.eacl-long)
Copied to clipboard
Bolei Ma, Yong Cao, Indira Sen, Anna-Carolina Haensch, Frauke Kreuter, Barbara Plank, Daniel Hershcovich
| Challenge: | Large Language Models (LLMs) are increasingly used to simulate public opinion and other social phenomena. |
| Approach: | They argue that open-endedness is essential for realistic social simulations . they argue that it captures expressiveness and individuality . |
| Outcome: | The proposed frameworks can improve measurement and design, support exploration of unanticipated views, and reduce researcher-imposed directive bias. |
Development and Evaluation of Pre-trained Language Models for Historical Danish and Norwegian Literary Texts (2024.lrec-main)
Copied to clipboard
| Challenge: | et al., 2019) develop and evaluate the first pre-trained language models specifically tailored for historical Danish and Norwegian texts. |
| Approach: | They develop and evaluate pre-trained language models specifically tailored for historical Danish and Norwegian texts. |
| Outcome: | The proposed model outperforms models trained on historical Danish and Norwegian literature in two downstream NLP tasks. |
Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking (2024.eacl-long)
Copied to clipboard
| Challenge: | Chinese geographic re-ranking task aims to find the most relevant addresses among retrieved candidates. |
| Approach: | They propose a framework to integrate Chinese geographic semantics into re-ranking pipelines. |
| Outcome: | The proposed framework improves on two Chinese benchmark datasets. |
What’s the Meaning of Superhuman Performance in Today’s NLU? (2023.acl-long)
Copied to clipboard
Simone Tedeschi, Johan Bos, Thierry Declerck, Jan Hajič, Daniel Hershcovich, Eduard Hovy, Alexander Koller, Simon Krek, Steven Schockaert, Rico Sennrich, Ekaterina Shutova, Roberto Navigli
| Challenge: | Recent research has focused on developing larger pretrained language models and introducing benchmarks such as SuperGLUE and SQuAD to measure their abilities. |
| Approach: | They propose to use benchmarks such as SuperGLUE and SQUAD to evaluate PLMs' abilities in language understanding, reasoning, and reading comprehension to assess their performance. |
| Outcome: | The proposed benchmarks have serious limitations affecting comparison between humans and PLMs and provide recommendations for fairer and more transparent benchmarks. |
Noise, Novels, Numbers. A Framework for Detecting and Categorizing Noise in Danish and Norwegian Literature (2024.emnlp-main)
Copied to clipboard
Ali Al-Laith, Daniel Hershcovich, Jens Bjerring-Hansen, Jakob Parby, Alexander Conroy, Timothy Tangherlini
| Challenge: | This study examines the literary perceptions of noise during the Scandinavian "Modern Breakthrough" period (1870-1899). |
| Approach: | They propose a framework for detecting and categorizing noise in literary texts from the late 19th century. |
| Outcome: | The proposed framework can be applied to Danish and Norwegian literature from the late 19th century. |
Pay More Attention to Relation Exploration for Knowledge Base Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches focus on entity representation and final answer reasoning, which results in limited supervision for this task. |
| Approach: | They propose a framework that utilizes relations to enhance entity representation and introduce additional supervision. |
| Outcome: | The proposed framework improves the F1 score on two benchmark datasets by 5.8% . it improves by 6.7% on WebQSP, better than state-of-the-art methods . |
Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations (2025.naacl-long)
Copied to clipboard
| Challenge: | Prior work has focused on using large language models to simulate human behaviors . but, LLMs are known to generate erroneous, stereotypical, or overconfident answers . |
| Approach: | They propose to specialize large language models for simulating survey response distributions by first-token probabilities. |
| Outcome: | The proposed model outperforms other methods and zero-shot classifiers on unseen questions, countries, and a completely unseened survey. |
Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Current knowledge is limited on whether cultural features can predict cross-cultural transfer learning success for subjective tasks. |
| Approach: | They advocate integration of cultural information into datasets and cultural adaptability . findings suggest cultural features can predict cross-cultural transfer learning success . |
| Outcome: | The findings suggest that cultural features can predict cross-cultural transfer learning success in OLD tasks. |
On Evaluating Multilingual Compositional Generalization with Translated Datasets (2023.acl-long)
Copied to clipboard
| Challenge: | a growing amount of research investigating compositional generalization in NLP is done on English . a critical semantic distortion is a limitation of the translation of datasets . |
| Approach: | They propose to translate a dataset for evaluating compositional generalization in semantic parsing. |
| Outcome: | The proposed benchmarks show that the translation of the MCWQ dataset suffers from semantic distortion. |
Multitask Parsing Across Semantic Representations (P18-1)
Copied to clipboard
| Challenge: | UCCA parsing is a test case for multitask learning, with auxiliary tasks AMR, SDP and Universal Dependencies (UD) . Semantic parsers have arguably yet to reach their full potential due to the limited amount of semantically annotated training data. |
| Approach: | They propose a general transition-based parser that can parse UCCA, AMR, SDP and Universal Dependencies (UD) they use a transition-driven learning architecture and a uniform transition-basic learning architecture to train the parsers. |
| Outcome: | The proposed parser improves UCCA, AMR, SDP and Universal Dependencies (UD) parsing over training in English, German and French. |
Rewarding Coreference Resolvers for Being Consistent with World Knowledge (D19-1)
Copied to clipboard
Rahul Aralikatte, Heather Lent, Ana Valeria Gonzalez, Daniel Hershcovich, Chen Qiu, Anders Sandholm, Michael Ringaard, Anders Søgaard
| Challenge: | Unresolved coreference is a bottleneck for relation extraction systems . a state-of-the-art system may be able to infer the relation using distributional information about the phrase the Sunshine State, but is likely to have limited evidence for the decision that it is coreferential with Florida rather than with Skynyrd. |
| Approach: | They propose to forward coreference input to relation extraction system and reward them for producing triples that are found in knowledge bases. |
| Outcome: | The proposed approach improves over the state-of-the-art by forwarding their input to a relation extraction system and rewarding resolvers for producing triples that are found in knowledge bases. |
Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics (2020.coling-main)
Copied to clipboard
| Challenge: | a systematic comparative analysis of linguistic meaning representations from different frameworks is needed. |
| Approach: | They compare a rule-based converter and a supervised delexicalized parser to map meaning representations from different frameworks. |
| Outcome: | The proposed method yields surprisingly accurate representations close to fully supervised UCCA parser quality. |
Argument Invention from First Principles (P19-1)
Copied to clipboard
Yonatan Bilu, Ariel Gera, Daniel Hershcovich, Benjamin Sznajder, Dan Lahav, Guy Moshkowich, Anael Malet, Assaf Gavron, Noam Slonim
| Challenge: | Argument Invention is a task that is often referred to as a natural way of inventing arguments, but has not been formalized in the context of NLP. |
| Approach: | They propose to define a taxonomy of recurring arguments and to automatically identify which of them are relevant to the topic. |
| Outcome: | The proposed taxonomy is coherent, covers the relevant topics and coincides with what debaters actually argue in their speeches, and facilitates automatic argument invention for new topics. |
HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signals (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a dataset of vibration haptic signals is developed to match descriptions to vibrations . a lack of large datasets annotated with textual descriptions is a challenge . |
| Approach: | They propose a multimodal dataset and task to match user descriptions to vibration haptic signals. |
| Outcome: | The proposed dataset matches user descriptions to vibration haptic signals . the results show that language models and audio models perform better than existing models . |
What does the Failure to Reason with “Respectively” in Zero/Few-Shot Settings Tell Us about Language Models? (2023.acl-long)
Copied to clipboard
| Challenge: | In the context of natural language inference, we examine how language models reason with respective readings from two perspectives: syntactic-semantic and commonsense-world knowledge. |
| Approach: | They propose a controlled synthetic dataset WikiResNLI and a naturally occurring dataset NatResLI to encompass various explicit and implicit realizations of "respectively". |
| Outcome: | The proposed datasets include explicit and implicit readings of "respectively" the proposed dataset shows that fine-tuned models struggle with understanding readings without explicit supervision. |
Probing for Hyperbole in Pre-Trained Language Models (2023.acl-srw)
Copied to clipboard
| Challenge: | Hyperbole is a common figure of speech that involves the use of exaggerated language for emphasis or effect. |
| Approach: | They conduct edge and minimal description length probing experiments on three pre-trained language models to explore the extent to which hyperbolic information is encoded . they also annotate 63 hyperbole sentences from the HYPO dataset according to an operational taxonomy to conduct an error analysis to explore encoding of different hyperboli categories. |
| Outcome: | The results show that hyperbole is encoded in a limited extent in pre-trained models and mostly in the final layers. |
When Do Language Models Endorse Limitations on Human Rights Principles? (2026.findings-eacl)
Copied to clipboard
Keenan Samway, Miu Nicole Takagi, Rada Mihalcea, Bernhard Schölkopf, Ilias Chalkidis, Daniel Hershcovich, Zhijing Jin
| Challenge: | a recent study evaluated how large language models navigate trade-offs involving the Universal Declaration of Human Rights. |
| Approach: | They evaluate how large language models navigate trade-offs involving the Universal Declaration of Human Rights (UDHR) they use 1,152 synthetically generated scenarios across 24 rights articles and eight languages . |
| Outcome: | The proposed models accept limiting economic, social, and cultural rights more often than political and civil rights, the authors show . their models show significant cross-linguistic variation with elevated endorsement rates of rights-limiting actions in Chinese and Hindi compared to English or Romanian . |
A Two-Sided Discussion of Preregistration of NLP Research (2023.eacl-main)
Copied to clipboard
| Challenge: | et al. (2021) suggest NLP research should adopt preregistration to prevent fishing expeditions and promote publication of negative results. |
| Approach: | et al. suggest NLP research should adopt preregistration to prevent fishing expeditions and promote publication of negative results. |
| Outcome: | The proposed approach solves many methodological problems with NLP research. |
FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture (2024.emnlp-main)
Copied to clipboard
Wenyan Li, Crystina Zhang, Jiaang Li, Qiwei Peng, Raphael Tang, Li Zhou, Weijia Zhang, Guimin Hu, Yifei Yuan, Anders Søgaard, Daniel Hershcovich, Desmond Elliott
| Challenge: | FoodieQA is a manually curated, fine-grained image-text dataset capturing the intricate features of food cultures across various regions in China. |
| Approach: | They evaluate vision–language Models and large language models on unseen food images and corresponding questions. |
| Outcome: | The proposed dataset evaluates vision–language Models and large language models on unseen food images and corresponding questions. |
Challenges and Strategies in Cross-Cultural NLP (2022.acl-long)
Copied to clipboard
Daniel Hershcovich, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, Anders Søgaard
| Challenge: | Various efforts have been made to accommodate linguistic diversity and serve speakers of many different languages. |
| Approach: | They propose a framework to examine cultural differences in NLP to better serve users . they argue that cultural knowledge, preferences and values can affect NLP practices . |
| Outcome: | The proposed framework examines how cultural knowledge, preferences and values can affect NLP practices. |
Towards Climate Awareness in NLP Research (2022.emnlp-main)
Copied to clipboard
| Challenge: | Increasing focus on efficient AI and NLP research lacks systematic climate reporting guidelines . a proposed model card would be practical with limited information about experiments and the underlying computer hardware. |
| Approach: | They propose a model card that is practically usable with limited information about experiments and the underlying computer hardware. |
| Outcome: | The proposed model card would be usable with limited information about experiments and the underlying computer hardware. |
Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys (2024.findings-eacl)
Copied to clipboard
| Challenge: | integrating cultural dimensions with dialogue encoding features can enhance the predictive accuracy and quality of dialogue agents. |
| Approach: | They propose to incorporate cultural dimensions into dialogue encoding features to enhance the predictive accuracy of dialogue agents. |
| Outcome: | The proposed model improves the accuracy and quality of dialogue predictions by incorporating cultural dimensions with dialogue encoding features. |
Dying or Departing? Euphemism Detection for Death Discourse in Historical Texts (2025.coling-main)
Copied to clipboard
Ali Al-Laith, Alexander Conroy, Jens Bjerring-Hansen, Bolette Pedersen, Carsten Levisen, Daniel Hershcovich
| Challenge: | euphemisms are a linguistic device used to soften discussions of uncomfortable topics . euphorias are used to refer to death in a less direct manner during a period of secularization . |
| Approach: | They propose to use a corpus of Danish and Norwegian novels to detect death-related euphemisms . they use pre-trained language models to detect euphoric and literal references to death . |
| Outcome: | The proposed method improves on state-of-the-art language models. |
Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users (2025.acl-long)
Copied to clipboard
Antonia Karamolegkou, Malvina Nikandrou, Georgios Pantazopoulos, Danae Sanchez Villegas, Phillip Rust, Ruchira Dhar, Daniel Hershcovich, Anders Søgaard
| Challenge: | Despite high adoption rate of Large Language Models, there are limitations related to contextual understanding, cultural sensitivity, and complex scene understanding. |
| Approach: | They conduct a user survey to identify adoption patterns and key challenges users face with such technologies. |
| Outcome: | The proposed models have high adoption rates but still face limitations in visual aids. |
Can AMR Assist Legal and Logical Reasoning? (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) has been shown to be useful for many downstream tasks. |
| Approach: | They propose neural architectures that utilize linearised AMR graphs in combination with pre-trained language models to capture logical relationships on multiple choice question answering tasks. |
| Outcome: | The proposed models outperform text-only baselines but outperformed text models, suggesting complementary abilities. |
UniMEEC: Towards Unified Multimodal Emotion Recognition and Emotion Cause (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies treat emotion recognition and emotion cause extraction as two individual problems, ignoring their natural causality. |
| Approach: | They propose a Unified Multimodal Emotion recognition and Emotion-Cause analysis framework to explore the causality between emotion and emotion cause. |
| Outcome: | The proposed framework reformulates MERC and MECPE tasks as mask prediction problems and unifies them with a causal prompt template. |
Content Differences in Syntactic and Semantic Representation (N19-1)
Copied to clipboard
| Challenge: | Syntactic analysis plays an important role in semantic parsing, but the nature of this role remains a topic of ongoing debate. |
| Approach: | They propose to use Universal Dependencies and UCCA as test cases to compare syntactic and semantic schemes. |
| Outcome: | The proposed comparison methodology can be used for fine-grained evaluation of UCCA parsing, highlighting both challenges and potential sources for improvement. |
Do LLMs Understand Wine Descriptors Across Cultures? A Benchmark for Cultural Adaptations of Wine Reviews (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in large language models have opened the door to culture-aware language tasks. |
| Approach: | They propose to integrate regional taste preferences and culture-specific flavor descriptors into wine reviews across Chinese and English. |
| Outcome: | The proposed model incorporates regional taste preferences and culture-specific flavor descriptors into the translation process. |
HapticLLaMA: A Multimodal Sensory Language Model for Haptic Captioning (2026.findings-eacl)
Copied to clipboard
| Challenge: | haptic captioning is the task of generating natural language descriptions from haptics, such as vibrations, for use in virtual reality and rehabilitation applications. |
| Approach: | They propose a multimodal sensory language model that interprets vibration signals into descriptions in a given sensory, emotional, or associative category. |
| Outcome: | The proposed model interprets vibration signals into descriptions in a given sensory, emotional, or associative category. |
Generalized Quantifiers as a Source of Error in Multilingual NLU Benchmarks (2022.naacl-main)
Copied to clipboard
| Challenge: | Quantifiers are pervasive in NLU benchmarks and their occurrence at test time is associated with performance drops. |
| Approach: | They propose a generalized quantifier NLI task to quantify their contribution to the errors of NLU models. |
| Outcome: | The proposed model is based on a generalized quantifier theory and is compared with pre-trained models. |