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 136
Host-Aware Web Crawling for LLM Pretraining Data
Web crawling is a major source of large language model (LLM) pretraining data, yet data-selection pipelines discard a large share of crawled pages.Taking Tokenization off the Host for Agentic LLM Serving
Agentic workloads resend long contexts that barely change between calls.Exploring Attention Sinks in Text-to-Image Transformers from Diffusion and Autoregressive Models
Attention sinks are tokens or positions that consistently receive disproportionate attention mass, often beyond what their semantic content would suggest.Test-Time Memory Construction
Large Language Models (LLMs) struggle to answer questions over long interaction histories, where relevant evidence may be scattered across distant sessions.Overcoming Data Imbalances with Expert Selection Biases
Mixture-of-Experts (MoE) models have become the standard architecture for frontier LLMs.From Structure to Validity: Mechanism-Guided Generation and Refinement of LLM Rubrics
Rubrics have been widely used to evaluate and optimize language models on open-ended tasks.MoPrO-SD: Modular Prompt Optimization for Stance Detection
Stance detection remains challenging for large language models (LLMs) due to implicit opinions, sarcasm, and context-dependent expressions of stance.ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents
Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to generate a repository from a given requirements…Towards the Roof of the World: NLP Progress in Tibetan Languages
Tibetan, spoken by some seven million people on and around the Qinghai-Xizang Plateau, remains underrepresented in natural language processing (NLP).Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR
Earnings call transcription presents a realistic continual learning scenario where Automatic Speech Recognition (ASR) systems are updated with new recordings but risk catastrophic forgetting of…Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization
Recent accent classification systems can achieve high accuracy in standard in-corpus evaluations.Oído: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator
Speech recognition on low-cost microcontrollers is, in practice, limited to keyword spotting or a fixed list of commands.Towards Enriching Design-Time Models with Evidence from Simulation and Operational Activities
Cyber-Physical Systems are developed through multiple model based activities, comprising several stages of development.A Better Metric Will Not Save You: What You Compare Beats How You Compare It
Representational similarity measures (RSA, CKA, Procrustes) are chosen for the transformations they treat as irrelevant, and all of them take the set of conditions as given.Proactive Agentic Orchestration
Agentic orchestration delegates tasks to sub-agents with independent contexts, providing a key path to extending the effective execution horizon of large language model agents.Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis
Clinical prognosis requires integrating structured measurements, physiological waveforms, longitudinal history, and population context.S-Space: Exploring Spatial Workspace in Multimodal Language Models
Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly understood.Personalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear?
Recent speech LLMs can leverage rich paralinguistic cues, enabling more complex and personalized interactions.Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution
Repository-level issue-resolution benchmarks such as SWE-bench evaluate submitted patches primarily based on whether they pass the correctness tests, leaving the runtime performance of different…Measuring Artifact Reliance in Machine-Generated Text Detectors
Detectors of machine-generated text score almost perfectly on scientific-literature benchmarks, implying we can reliably distinguish with these detectors human and machine-generated documents.