Natural Language Processing

Researchers introduced EXPO-SQL, a reinforcement learning method that assigns clause-level rewards to improve text-to-SQL query generation. By analyzing execution results and error messages, the method outperforms existi…

Researchers propose ModTGCN, a modularity-aware graph neural network for text classification that jointly optimizes cross-entropy and a modularity-based auxiliary objective to promote class-coherent document communities.…

Researchers introduced the Normalized Context Utilization (NCU) metric to quantify contextual information gain in Retrieval-Augmented Generation (RAG) systems, revealing that small language models (SLMs) match or outperf…

Researchers developed a framework using large language models to quantify product desirability from qualitative feedback, achieving up to 0.97 Pearson correlation and 94% accuracy on two Product Desirability Toolkit data…

Researchers propose a training-free IBA framework for Knowledge-Based VQA that decouples entity identification from evidence re-ranking, outperforming fine-tuned baselines on Encyclopedic-VQA and InfoSeek while reducing …

A new study auditing eight automatic attribution metrics across multiple datasets finds that no single metric consistently performs best, with rankings inverting across datasets (Kendall tau = -0.64). The instability lea…

Researchers introduced QuechuaTok, a benchmark evaluating tokenization strategies for Southern Quechua, a low-resource agglutinative language. They found that BPE achieved the lowest fertility rate but only 6.67% morphol…

Researchers introduced the MELD dataset to evaluate whether embedding models capture mathematical equivalence, finding that current models group statements by terminology rather than underlying math. They proposed a cont…

Researchers introduced RASC+, a retrieval-constrained LLM adjudication method for clinical value set authoring, achieving a candidate-pool recall of 0.730 on the RASC benchmark. Using GPT-5 as a constrained adjudicator, …

Researchers propose Prompt-Vision Token Activation Map (PV-TAM) to improve vision-language consistency in large vision-language models by using prompt-side semantics and filtering systematic bias from modality boundary m…

Researchers introduced HANCLIP, a family of vision-language models that restructure the embedding space to handle negation by combining hyperbolic and angular objectives. Trained on 20,000 image-text quadruplets, HANCLIP…

Researchers introduced Token-to-Token alignment, a framework that establishes explicit semantic correspondence between tokens across prompts in text-to-image models. The method rephrases prompts into a structured form an…

A new study on arXiv systematically examines the order of preprocessing techniques for sentiment analysis on Twitter datasets, finding that tokenisation is the most impactful technique while spelling correction is the le…

Researchers discovered sentence-level contextual entrainment in large language models, where sentences in prompts increase their probability during inference even if counterfactual. The phenomenon decreases with model si…

Researchers constructed large-scale algorithm co-occurrence networks in natural language processing based on full-text academic papers, analyzing their structural characteristics and centrality measures. The study found …

Researchers introduced VeryTrace, a zero-shot verification-and-repair framework that formalizes Chain-of-Thought reasoning traces into a compilable Domain-Specific Language, enabling step-level error detection and correc…

A new study from arXiv shows that multilingual encoder initialization benefits streaming automatic speech recognition (ASR) only at low target-language data scales, with the advantage decaying as data increases. Across e…

Nylas has released a CLI tool and API pattern for extracting one-time passcodes (OTP) and two-factor authentication (2FA) codes from email. The CLI's `nylas otp get` and `nylas otp watch` commands allow developers to pul…

A paper by Saha et al. (arXiv 2506.07001) demonstrates that detector-guided paraphrasing using RoBERTa as a reward reduces the true positive rate of AI-generated text detectors by 87.88% across Binoculars, Fast-DetectGPT…

LectuLibre built a robust EPUB parsing and rebuilding pipeline in Python to translate entire books while preserving visual structure. The team used ebooklib for metadata handling and lxml for fast, namespace-aware XHTML …