arXiv Machine Learning August 17, 2026 By Benjam\'in Schindler, Gonzalo A. Ruz

Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification

Read the original on arXiv Machine Learning →

arXiv:2608. 13866v1 Announce Type: new Abstract: Large language models (LLMs) can generate synthetic training data for text classification, but the quality of generated samples is heterogeneous: some fall in correct class regions of the embedding space while others land in peripheral or cross-class zones.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Jul 20

PRiSM: Prototype Regularization for Few-Shot VLMs

Training-free few-shot adaptation methods have gained significant attention recently in the context of Vision-language Models (VLMs). Yet, current benchmarks rely on strong assumptions about the statistics of the adaptation data, e.

llms multimodal benchmarks safety

arXiv Machine Learning

Jun 2

GottBERT: a pure German Language Model

arXiv:2012. 02110v2 Announce Type: replace-cross Abstract: Pre-trained language models have significantly advanced natural language processing (NLP), especially with the introduction of BERT and its optimized version, RoBERTa.

By Raphael Scheible, Johann Frei, Fabian Thomczyk, Henry He, Patric Tippmann, Jochen Knaus, Victor Jaravine, Frank Kramer, Martin Boeker

llms nlp

arXiv Machine Learning

Jun 26

LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots

arXiv:2605. 24417v2 Announce Type: replace Abstract: Supervised classification on tabular data remains a central machine learning task, but its dependence on large labeled datasets limits its applicability in data-scarce settings.

By Daria Grushina, Kseniia Kuvshinova, Alina Kostromina, Aziz Temirkhanov, Mile Mitrovic, Dmitry Simakov

llms benchmarks

arXiv AI

Jul 16

Data-Efficient Adaptation of LLMs via Attention Head Reweighting

arXiv:2607. 13425v1 Announce Type: cross Abstract: Learning effectively from limited data is critical in domains like security where labeled examples are scarce.

By Tuomas Oikarinen, Zixiao Chen, Charlotte Siska, Tsui-Wei Weng, Chandan Singh, Jianfeng Gao

llms nlp fine-tuning

arXiv Machine Learning

Jul 28

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models

arXiv:2607. 23052v1 Announce Type: cross Abstract: Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries like "umbrella and no person" retrieve images containing both, even when concept detection is reliable.

By Sultan Alshehri, Zhantao Yang, Han Zhang, Marios Savvides

llms rag fine-tuning multimodal

arXiv AI

Jul 7

Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repetition Probability

arXiv:2607. 04061v1 Announce Type: cross Abstract: Distinguishing Large Language Model (LLM) generated text from human writing is a critical and difficult challenge.

By Christopher Nassif, Josh F. Cooper

llms benchmarks safety

Related stories

PRiSM: Prototype Regularization for Few-Shot VLMs

GottBERT: a pure German Language Model

LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots

Data-Efficient Adaptation of LLMs via Attention Head Reweighting

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models

Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repetition Probability