Different Perturbations, Different Mechanisms: Understanding Continued Pre-training for Zero-Shot Dialect Robustness
August 8, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2608.05510v1 Announce Type: new Abstract: Dialectal variation remains a major challenge for multilingual language models...
Did You Forget What I Asked? Prospective Memory Failures in Large Language Models
März 26, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2603.23530v1 Announce Type: new Abstract: Large language models often fail to satisfy formatting instructions when...
Did I Faithfully Say What I Thought? Bridging the Gap Between Neural Activity and Self-Explanations in Large Language Models
Juni 13, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2506.09277v2 Announce Type: replace Abstract: Large Language Models (LLM) have demonstrated the capability of generating...
DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction
Oktober 21, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2510.09211v2 Announce Type: replace Abstract: When performing reasoning tasks with user-specific requirements, such as strict...
DIALEVAL: Automated Type-Theoretic Evaluation of LLM Instruction Following
März 5, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2603.03321v1 Announce Type: new Abstract: Evaluating instruction following in Large Language Models requires decomposing instructions...
DiaBlo: Diagonal Blocks Are Sufficient For Finetuning
Juni 5, 2025admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2506.03230v1 Announce Type: cross Abstract: Finetuning is a critical step for adapting large language models...
DG^VoiC: Speaker Clustering for Fraud Investigation under Real Call-Centre Conditions
Juni 29, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2606.28048v1 Announce Type: cross Abstract: Insurance fraud remains costly and operationally difficult, particularly in call-centre...
DFKI-MLT at SemEval-2026 TASK 7: Steering Multilingual Models Towards Cultural Knowledge
Mai 25, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)arXiv:2605.23069v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used across diverse linguistic...
Developing an End-to-End Document Intelligence Pipeline with docTR for OCR, Layout Analysis, KIE, Benchmarking, and Searchable PDFs
August 17, 2026admin NUAI,Committee,Nachrichten,Uncategorized(0)In this tutorial, we develop an end-to-end OCR workflow with docTR and explore how modern...
