AI & Machine Learning · Computer Science & AI
Computation & Language / NLP
The newest papers in Computation & Language / NLP that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 17 September 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Computation & Language / NLP every morning.
Follow Computation & Language / NLP and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 50
RefinedGAW: A Refined German Academic Web Dataset
The largest open German text datasets are built from broad web crawls, which provide scale but limited coverage of specific domains.Large Language Models: A Plain-Language Overview for Engineers
Large language models (LLMs) are neural networks trained on huge text collections to generate text by predicting what comes next.HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding
Tabular data is widely used in scientific applications, where complex layouts, including multi-level headers, merged cells, captions, and footnotes, make information extraction difficult.Does the Outfit Change the Price? Context Halo in Vision-Language Model Valuation of an Identical Low-Cost Necklace
A chunky gold-tone chain necklace bought online for 2.43 USD was photographed four ways: worn with formal attire against a wood-panelled wall, worn at a party, worn with casual clothing in a…One Mean Log-Mel Vector per Phoneme: Simple and Fast Text Injection for Speech Recognition
Text injection trains speech recognition models on unpaired text alongside paired audio.Entity Matching using Decision Models
Entity matching is the task of deciding whether two records describe the same real-world entity.Cross-Loop Query Handoff: How Later Loops Redirect Two-Hop Retrieval in the Ouro Looped Language Models
How do later loops in a pretrained looped language model repair two-hop retrieval?DuQUAD: A Dual-View Framework with Quality-Aware Evidence Pruning for Multi-Document Question Answering
Large language models with retrieval-augmented generation systematically underutilize evidence in the middle of multi-document contexts, a phenomenon known as Lost in the Middle.Examining form-based linguistic productivity in people and large language models
Linguistic productivity, as evidenced by the use of words in novel contexts, is one of the most striking facts about human language.Perturbation-Based Data Selection for Medical Question Answering
Selecting a compact training subset is an important step in adapting medical language models from existing question-answering banks.Quantifying Meaning with SCAPE-T: Semantic Complexity from Encoder-Only Transformer Attention
Automated semantic complexity estimation remains underexplored in NLP, despite important applications in linguistics and interpretability.Adaptive Transfer of Representational Signatures for LLM Reliability Detection
Large language models (LLMs) are reported to be susceptible to reliability issues including hallucinations and reasoning errors.Propasafe-Hybrid: A Text-Based Hybrid Propaganda Detection Tool
Propagandistic content increasingly circulates through online news and social media, where readers often encounter it with limited scrutiny, highlighting the need for reliable and fine-grained…Incremental Predictive Value of LLM Tutoring Interactions for Student Performance
We evaluate whether semester-level interaction features from a large language model tutor improve assignment-score prediction beyond constant baselines.Small Edits, Shifting Decisions: Benchmarking LLM Accuracy and Reliability on French Input Variants
French users may omit apostrophes and diacritics or make keyboard typos in everyday input.Five Architectures, One Shared Space Cross-Model Representational Alignment Without Weight Merging
Combining language models is usually done by averaging weights, which works only when the models share a common starting point.Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce novelty assessments…Towards a Learnable Retriever for Textual Graph Question Answering
Textual graph question answering (GraphQA) and graph-based retrieval-augmented generation (GraphRAG) have gained increasing attention as a way to ground large language models (LLMs) on structured…Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL
Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks.One Model, Two Paths: Balancing Single-Pass and Looped Performance in Language Models
Repeating Transformer layers can improve language-model performance without adding parameters.