arXiv Machine Learning
Jun 25
Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models
arXiv:2605. 31220v2 Announce Type: replace-cross Abstract: Confidence estimation (CE), i.
ProBel: Propaganda Detection with Techniques, Spans, and Explanations
ProBel is a bilingual Arabic and English resource for propaganda detection that aligns binary labels, multi-label annotations for 23 propaganda techniques grouped into six categories, technique-labeled spans, and reference explanations for news sentences. The dataset supports matched binary, coarse-grained, multi-label, and span-level tasks in both languages, and the authors evaluate zero‑shot prompting, task‑specific fine‑tuning, and joint training. A single bilingual multi‑task model achieves the best overall performance, with cross‑task analysis revealing that joint classification preserves binary performance while span‑only training can weaken sentence‑level prediction, and that joint bilingual training yields the most stable results.
Related stories
arXiv AI
2d ago
PolERo: Studying Political Evasion in Romanian
PolERo presents a new dataset of 3,574 Romanian question‑answer pairs from presidential transcripts, annotated for political evasion using a two‑level taxonomy of response clarity and fine‑grained evasion strategies. The study evaluates various classification methods—including TF‑IDF baselines, fine‑tuned encoders, a sliding‑window encoder, and zero/few‑shot LLM prompting—under matched conditions. Cross‑lingual transfer experiments via joint bilingual training and machine‑translation augmentation reveal that fine‑tuned encoders perform competitively, transfer is asymmetric, and ambivalent evasion categories with pragmatic cues remain the most challenging across all models.
arXiv Machine Learning
Jul 22
Translation as Augmentation: Effect of Translated Data on Assessment of Difficulty
arXiv:2607. 19101v1 Announce Type: cross Abstract: Reliable Text Difficulty Assessment is a prerequisite for valid text simplification workflows and personalized learning applications.
arXiv AI
Jul 28
Flick: Few Labels Text Classification using K-Aware Intermediate Learning in Multi-Task Low-Resource Languages
arXiv:2506. 10292v2 Announce Type: replace-cross Abstract: Training deep learning networks with minimal supervision has gained significant research attention due to its potential to reduce reliance on extensive labelled data.
arXiv Machine Learning
Aug 4
LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering
arXiv:2604. 03532v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult.
arXiv Computation and Language
5d ago
Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization
The paper investigates whether large language models can learn and reproduce annotator‑specific label‑explanation behavior, using two sentence‑pair tasks with four annotators each. It finds that individual annotator patterns are weak at the single‑annotation level but become detectable after reducing input‑content effects and aggregating across annotators. The authors propose cross‑annotator preference optimization (CAPO), which improves upon prompting and supervised fine‑tuning by better capturing annotator‑specific reasoning while maintaining stable attribution.
Hugging Face Trending Papers
Jul 1
MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages
Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synthetic parallel corpus with approximately 4.
arXiv Machine Learning
Aug 24
MIL-BERT: Classification of Arbitrarily Large Text with Performance and Explanatory Guarantees
MIL-BERT is a neural network algorithm that classifies large texts by selecting relevant excerpts, inspired by multiple instance learning. It scales to samples with nearly 1 million tokens and has been evaluated on seven datasets, achieving state‑of‑the‑art results on three long‑text tasks such as political bias detection, trigger warning identification, and author demographic inference. The model also generalizes from weakly‑labeled text bags to accurately classify smaller instances.
arXiv Machine Learning
Jul 31
Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models
arXiv:2607. 27421v1 Announce Type: cross Abstract: Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable open-weight language models under compute, latency, and robustness constraints.
arXiv AI
Aug 12
A Cost-Efficient Routing Pipeline for Multilingual Short-Text Classification Using Small Language Models
arXiv:2608. 10939v1 Announce Type: cross Abstract: Multilingual short-text classification supports operational systems such as content moderation, customer support routing, and intent recognition, yet aggregate evaluation often hides large differences between high-resource and low-resource languages.
arXiv AI
Jun 16
Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes
arXiv:2606. 15307v1 Announce Type: cross Abstract: Hateful and propagandistic memes exploit the interplay between images and text to convey harmful intent that neither modality reveals alone.
arXiv AI
3d ago
Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation
The paper introduces Iterative MBR Distillation for Error Span Detection (ESD) in machine translation, a self‑evolution framework that replaces human annotations with pseudo‑labels generated by a large language model. By iteratively applying Minimum Bayes Risk decoding, the method produces high‑quality error spans without costly human effort. Experiments on WMT Metrics Shared Task datasets show that models trained solely on these pseudo‑labels outperform both unadapted baselines and supervised models trained on human data at system and span levels, while keeping sentence‑level performance competitive.