Imagen de Portada

Challenges in Explaining Pretrained Clinical Text Classifiers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Miok, Kristian, Klemen, Matej, Škrlj, Blaz, Šikonja, Marko Robnik
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning
por: Miok, Kristian, et al.
Publicado: (2025)

Measuring Catastrophic Forgetting in Cross-Lingual Transfer Paradigms: Exploring Tuning Strategies
por: Koloski, Boshko, et al.
Publicado: (2023)

Evaluating Metalinguistic Knowledge in Large Language Models across the World's Languages
por: Arčon, Tjaša, et al.
Publicado: (2026)

Neural spell-checker: Beyond words with synthetic data generation
por: Klemen, Matej, et al.
Publicado: (2024)

Towards Corpus-Grounded Agentic LLMs for Multilingual Grammatical Analysis
por: Klemen, Matej, et al.
Publicado: (2025)

Code-mixed Sentiment and Hate-speech Prediction
por: Yadav, Anjali, et al.
Publicado: (2024)

Solving Word-Sense Disambiguation and Word-Sense Induction with Dictionary Examples
por: Škvorc, Tadej, et al.
Publicado: (2025)

QFS-Composer: Query-focused summarization pipeline for less resourced languages
por: Đuranović, Vuk, et al.
Publicado: (2026)

Sarcasm Detection in a Less-Resourced Language
por: Đoković, Lazar, et al.
Publicado: (2024)

Improving LLMs for Machine Translation Using Synthetic Preference Data
por: Vajda, Dario, et al.
Publicado: (2025)

Incremental Graph Construction Enables Robust Spectral Clustering of Texts
por: Pranjić, Marko, et al.
Publicado: (2026)

Large language models for folktale type automation based on motifs: Cinderella case study
por: Arčon, Tjaša, et al.
Publicado: (2025)

Real-time News Story Identification
por: Škvorc, Tadej, et al.
Publicado: (2025)

Review of Natural Language Processing in Pharmacology
por: Trajanov, Dimitar, et al.
Publicado: (2022)

Generative Model for Less-Resourced Language with 1 billion parameters
por: Vreš, Domen, et al.
Publicado: (2024)

FuDoBa: Fusing Document and Knowledge Graph-based Representations with Bayesian Optimisation
por: Koloski, Boshko, et al.
Publicado: (2025)

AutoML-guided Fusion of Entity and LLM-based Representations for Document Classification
por: Koloski, Boshko, et al.
Publicado: (2024)

Retrieval-augmented code completion for local projects using large language models
por: Hostnik, Marko, et al.
Publicado: (2024)

Building a Strong Instruction Language Model for a Less-Resourced Language
por: Vreš, Domen, et al.
Publicado: (2026)

From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies
por: Škrlj, Blaž, et al.
Publicado: (2025)

Explaining Text Classifiers with Counterfactual Representations
por: Lemberger, Pirmin, et al.
Publicado: (2024)

Threats Assessment of the Endemic Idle Crayfish (Austropotamobius bihariensis Pârvulescu, 2019): Lessons From Long‐Term Monitoring
por: Andrei‐Robert Ács, et al.
Publicado: (2025)

STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond
por: Dycke, Nils, et al.
Publicado: (2024)

Agent0: Leveraging LLM Agents to Discover Multi-value Features from Text for Enhanced Recommendations
por: Škrlj, Blaž, et al.
Publicado: (2025)

Pretraining Exposure Explains Popularity Judgments in Large Language Models
por: Mozafari, Jamshid, et al.
Publicado: (2026)

RingSQL: Generating Synthetic Data with Schema-Independent Templates for Text-to-SQL Reasoning Models
por: Sterbentz, Marko, et al.
Publicado: (2026)

Harnessing the Intrinsic Knowledge of Pretrained Language Models for Challenging Text Classification Settings
por: Gao, Lingyu
Publicado: (2024)

HRM-Text: Efficient Pretraining Beyond Scaling
por: Wang, Guan, et al.
Publicado: (2026)

Table-to-Text Generation with Pretrained Diffusion Models
por: Krylov, Aleksei S., et al.
Publicado: (2024)

A Computational Framework for Interpretable Text-Based Personality Assessment from Social Media
por: Gjurković, Matej
Publicado: (2025)

Detecting and Explaining (In-)equivalence of Context-Free Grammars
por: Schmellenkamp, Marko, et al.
Publicado: (2024)

Generating Diverse Synthetic Datasets for Evaluation of Real-life Recommender Systems
por: Malenšek, Miha, et al.
Publicado: (2024)

Your Extreme Multi-label Classifier is Secretly a Hierarchical Text Classifier for Free
por: Bertalis, Nerijus, et al.
Publicado: (2024)

Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection
por: Turki, Yassine, et al.
Publicado: (2026)

Explaining Text Similarity in Transformer Models
por: Vasileiou, Alexandros, et al.
Publicado: (2024)

Tracking Semantic Change in Slovene: A Novel Dataset and Optimal Transport-Based Distance
por: Pranjić, Marko, et al.
Publicado: (2024)

Finding Challenging Metaphors that Confuse Pretrained Language Models
por: Li, Yucheng, et al.
Publicado: (2024)

The Data-Quality Illusion: Rethinking Classifier-Based Quality Filtering for LLM Pretraining
por: Saada, Thiziri Nait, et al.
Publicado: (2025)

Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
por: Gong, Linyuan, et al.
Publicado: (2023)

IT5: Text-to-text Pretraining for Italian Language Understanding and Generation
por: Sarti, Gabriele, et al.
Publicado: (2022)