Classical and neural NLP: translation, question answering, tokenization and the evaluation of language understanding.
arXiv:2608.30935v1 Announce Type: cross Abstract: Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embod...
arXiv:2608.30614v1 Announce Type: new Abstract: Organizing unstructured feedback text into hierarchical taxonomy is a fundamental challenge in NLP, particularly in domains where feedback arrives at m...
arXiv:2608.30163v1 Announce Type: cross Abstract: Real-world knowledge resides in multimodal documents, necessitating retrieval-augmented generation (RAG) for accurate question answering. However, ex...
arXiv:2608.31142v1 Announce Type: cross Abstract: The 2025--2026 AI market has seen a wave of stealth releases: frontier models launched anonymously on developer platforms under codenames. For their...
arXiv:2608.30679v1 Announce Type: cross Abstract: Large Reasoning Models produce Long Chains-of-Thought (LCoTs) which involve breaking down the problem into smaller reasoning steps before reaching th...
The paper presents a rigor‑matched audit comparing two periodic‑step, search‑based layer‑skipping methods for efficient large language model inference: a confidence‑gated early‑exit baseline (ConfLayers) and a self‑speculative decoding approach (SWIFT). Across two Qwen2.5 model scales and tasks (GSM8K reasoning and CNN/DailyMail summarization), SWIFT consistently outperforms ConfLayers in accuracy and, after separating search overhead, achieves faster true inference speed in most settings. The study also evaluates two trained‑routing methods (LayerRoute and LayerDrop), finding modest speedups but significantly lower accuracy, especially for LayerRoute on GSM8K at 1.5B.
Manacá-1B is a 1.72‑billion‑parameter, open decoder‑only language model trained from scratch for Brazilian Portuguese, released with a fully containerized, reproducible training pipeline and complete logs. The authors evaluate it against nine open baselines on four Portuguese benchmarks, reporting standard errors and paired significance tests, and find that Manacá-1B outperforms smaller models on LAMBADA‑PT while remaining competitive on commonsense completion. They also uncover a tokenizer‑related evaluation pitfall that can drastically lower accuracy and provide a simple fix, releasing all code, logs, and corrected tokenizer for full reproducibility.
arXiv:2608.31038v1 Announce Type: new Abstract: Incremental Named Entity Recognition (INER) stands as a pivotal task in information extraction, emphasizing the successive identification of new entity...
arXiv:2511.22707v2 Announce Type: replace-cross Abstract: In web environments, user preferences are often refined progressively as users move from browsing broad categories to exploring specific item...
arXiv:2605.06582v4 Announce Type: replace Abstract: Modern learning systems represent perceptual signals with continuous vectors, but comparison, retrieval, memory, alignment, and reasoning are often...
The paper compares generative and encoder-based neural models for multilingual Named Entity Recognition (NER) across the eleven languages of the Naamapadam benchmark. Five classic model families, four decoder-only large language models fine‑tuned with LoRA and 4‑bit NF4 quantisation, and nine generative models in zero‑to‑5‑shot inference were evaluated under strict CoNLL span‑level metrics. Encoder-based models (mBERT and XLM‑R) achieved substantially higher F1 scores—up to 0.675 on Hindi—than any generative architecture, with gaps of 7.5–40 percentage points; the best few‑shot result reached only 28% of the encoder baseline. The study identifies three language clusters (encoder‑dominant, partial‑coverage, and failure‑zone) and offers deployment guidelines based on transfer learning and low‑resource NLP principles.
arXiv:2608.30092v1 Announce Type: cross Abstract: We present Arkios, a 1.04B-parameter dense transformer pretrained from scratch on 150B tokens of bilingual English-Nepali text, using a custom single...
arXiv:2606.16206v2 Announce Type: replace Abstract: Large language models are increasingly proposed as educational tutors, yet stronger task-solving ability does not necessarily imply stronger learni...
arXiv:2608.29890v1 Announce Type: new Abstract: Biomedical Named Entity Recognition (NER) is fundamental to healthcare AI applications, including clinical decision support and medical information ext...
arXiv:2502.00857v2 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly provide direct answers to user questions, raising concerns about reduced engagement in critical thinking...
arXiv:2608.30425v1 Announce Type: new Abstract: Cross-lingual aspect-based sentiment analysis (ABSA) transfers knowledge from a source language with annotated data to a target language, enabling fine...
arXiv:2608.30297v1 Announce Type: new Abstract: Attributes describing data content and context can induce diverse imbalance patterns that go beyond label imbalance alone. However, existing studies pr...
arXiv:2601.12868v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly operate in high-stakes settings where demographic attributes such as race and ethnicity may be expl...
IndicQE-APE is a consolidated benchmark that unifies quality estimation (QE) and automatic post‑editing (APE) data for nine Indic language pairs, comprising 126,754 instances with multiple aligned labels such as direct assessment, human post‑edit, word‑level OK/BAD tags, and error explanations. The dataset includes a stratified test set across four difficulty axes and supports training and evaluation of six prompted large language models, three COMET metrics, and three APE systems. Experiments reveal that segments with conflicting holistic and token‑level quality signals are consistently ranked lower, while annotator disagreement shows no effect when controlled for score distribution. whyItMatters":"The benchmark provides a unified resource for training and evaluating QE and APE across Indic languages, enabling consistent comparison of models and metrics on a shared dataset."
arXiv:2608.30475v1 Announce Type: cross Abstract: We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation. It includes two tasks: (i) AynVQA, cove...