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 24
ArSciKids: Arabic Curriculum-Aligned Datasets for Scientific Experiment and Multiple-Choice Question Generation in Primary Education
Despite growing interest in Arabic natural language processing, curriculum-aligned educational resources remain scarce compared with English, and few public datasets for Arabic curriculum content…The Brittle Compass: Navigating LLM Prompt Sensitivity in Slovak Migration Media Discourse
In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance…MedAstra: ASR-less Speech Retrieval with Diagnostic Grounding for Medical QA
Spoken medical question answering can fail when automatic speech recognition (ASR) corrupts a clinically important term before retrieval.Does Random Search Discover Task Experts? Revisiting Neural Thickets
Pretrained models are typically viewed as generalists, requiring bespoke post-training to achieve task-specific expertise.EZ-Ar-VC: Robust Arabic Voice Anonymization with Generalization across Dialects and Code-Switching
Voice conversion (VC) models can be used to anonymize speech data while preserving naturalness.Geometry of Confabulation and Refusal in Small Language Models
Faced with an unanswerable question, small language models can either refuse or confabulate: confidently produce a wrong answer.Character-Name Concentration in LLM Fiction: Measuring Displacement and Mitigating Repetition
Character names in large language model (LLM) fiction concentrate on a handful of recurrent names such as 'Elara' and 'Elias', a measurable face of AI slop.CuriousTogether: Implications of Curiosity and Cultural Grounding in Multi-Agent LLM Interactions
Large Language Models (LLMs) are increasingly deployed in multi-agent settings, exhibiting emergent collective behaviors, yet the role of curiosity as a driver of such dynamics remains understudied.When LLMs Modify Themselves: Convergence, Values, and Stopping in Iterative Self-Improvement
What happens when language models are given tools to iteratively modify their own system prompts?What Do LLM Judges Actually Verify? Matched Controls and Record Gaps for Document Currency
LLM judges often check, against an amendment record, whether the documents an answer cites are still in force.Are Fake Citations a Form of Reward Hacking? A Pre-Registered Study of Post-Training and Citation Cues
Post-trained language models fabricate citations at high rates.Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference
Diffusion large language models (dLLMs) generate tokens in parallel via iterative denoising, but their bidirectional attention prevents the KV caching used by autoregressive models and recomputes…Sentiment sensing: comparative analysis of multilingual sentiment dynamics
Cross-country sentiment analysis faces three fundamental challenges: language-specific biases distort comparisons, compositional data constraints invalidate standard statistics and temporal dynamics…Wrong Together: Shared Bias in User Simulation
User simulators generate responses in place of human participants, allowing researchers to estimate the result of a study.Interpreting Classical Readability Formulae as Surprisal
Surprisal correlates closely with reading time and is widely used in the cognitive science of reading as a measure of processing difficulty.MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation
Self-distillation methods for large language models with an exponential moving average (EMA) teacher already retain a history of student updates.Language Models Show a "Women-Are-Wonderful" Effect in Blame Attribution That is Not Just Leniency
This paper investigates the Women-Are-Wonderful (WaW) effect in language-model blame attribution: a favorable bias in which women receive more positive evaluations than men.HyperRepair: Recovering Forgotten General Capabilities of Fine-Tuned Language Models
Fine-tuning improves a language model's performance in a target domain but can weaken its general capabilities.Lineage Is Memory: Parent Inheritance and Feedback Disclosure in Short-Budget LLM-Guided Optimization
Iterative language-model optimizers refine prompts and programs by evaluating a candidate, showing a proposer model a sample of failing cases, and keeping revisions that improve performance.Context as Infrastructure: Knowledge Compilation for Retrieval in Agentic Systems with Harnesses
Retrieval-augmented generation is becoming agentic.