Nachrichten
Team “better_call_claude”: Style Change Detection using a Sequential Sentence Pair Classifier
arXiv:2508.00675v1 Announce Type: new Abstract: Style change detection – identifying the points in a document...
Teaching the model: Designing LLM feedback loops that get smarter over time
How to close the loop between user behavior and LLM performance, and why human-in-the-loop systems...
Teaching AI to Say ‘I Don’t Know’: A New Dataset Mitigates Hallucinations from Reinforcement Finetuning
Reinforcement finetuning uses reward signals to guide the large language model toward desirable behavior. This...
Teaching AI to run with the turbines
Artificial intelligence may have captured the public imagination through chatbots and image generators, but some...
TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion
arXiv:2601.09633v1 Announce Type: new Abstract: Taxonomies form the backbone of structured knowledge representation across diverse...
TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora
arXiv:2506.10737v1 Announce Type: new Abstract: The rapid evolution of scientific fields introduces challenges in organizing...
Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languages
arXiv:2602.23388v1 Announce Type: new Abstract: The rising demand for inclusive speech technologies amplifies the need...
Take Out Your Calculators: Estimating the Real Difficulty of Question Items with LLM Student Simulations
arXiv:2601.09953v1 Announce Type: new Abstract: Standardized math assessments require expensive human pilot studies to establish...
Tailoring AI solutions for health care needs
The AI market is full of big promises of grand transformation. Health care is a...
Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack
arXiv:2501.08454v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have become essential tools for digital...
TAG-EQA: Text-And-Graph for Event Question Answering via Structured Prompting Strategies
arXiv:2510.01391v1 Announce Type: new Abstract: Large language models (LLMs) excel at general language tasks but...
Taalas is replacing programmable GPUs with hardwired AI chips to achieve 17,000 tokens per second for ubiquitous inference
In the high-stakes world of AI infrastructure, the industry has operated under a singular assumption:...
