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 31
Judged in Company: In-Context Batching Makes LLM Verdicts Depend on Other Items
To save cost, practitioners often ask a language model to grade many independent items in one prompt.When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications
To succeed in real-world long-horizon software development, coding agents must satisfy multi-dimensional task specifications, such as interface compatibility and error handling, and do so without…Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering
Large language models (LLMs) are increasingly capable, yet they produce wrong answers indistinguishable from correct ones.Latent Path Exploration via Potential-Guided Subtrajectory Balance
Continuous latent reasoning enables language models to perform intermediate computation without generating explicit reasoning traces.Leveraging Recourse and Size Bounds for OnlineKnapsack with Removable Items
In the online unweighted knapsack problem, items arrive sequentially and must be accepted or rejected immediately for a bounded-capacity knapsack, aiming to maximize the total size of accepted items.Decision and System One models in rheumatology: accuracy and calibration on specialty-training examination questions and diagnostic case vignettes
To evaluate the accuracy and calibration of Decision and System One models on rheumatology examination questions and diagnostic vignettes.Factorized Representations of Concurrent Temporal Variables in Pretrained Language Models
Language models often need to maintain multiple contextual variables that evolve independently within a document.Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation
Agents powered by large language models (LLMs) have demonstrated remarkable progress in solving complex reasoning tasks.Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records
Large language model (LLM) agents are proposed for clinical prediction but are untested in pediatrics, where cohorts are small and outcomes are uncommon.Scaling Mathematical Proof Supervision from Structured Textbooks
Mathematical supervision for language models is typically flattened into isolated problem-solution pairs, discarding the curricular organization and evidential structure of the original sources.Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success
Tool-use benchmarks often score agents by final task success, but terminal outcomes can obscure whether the intermediate tool-call trajectory was executable.Glance: The Generator Is Its Own Reranker
Retrieval-augmented generation commonly serves separate models for reranking and answering, duplicating model residency and passage processing.Training language models in simulation for psychiatric intake
In psychiatric practice, the clinical intake interview remains a primary diagnostic instrument, requiring the clinician to establish rapport while disentangling complex, overlapping presentations.FIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge
Financial AI workflows that reuse investor knowledge need persistent memory that integrates observations across sources and periods without losing identity or provenance.Preserving Utility in Continual LLM Unlearning via Orthogonal Projections
Unlearning concerns the task of removing the influence of a sensitive portion of the training data, such as protected, copyrighted or private text, from a model without retraining it from scratch.rTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment
Do research agents have taste, the judgment of which experiments are worth running before their outcomes are known?Agentic University: Collaborative Agents for Personalized Learning
Large language models support personalized tutoring, content generation, and adaptive learning paths.Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models
Voice-cloning TTS models synthesize an unseen speaker's voice from brief speech prompts, but it remains unclear which acoustic properties they represent and use.A Low-Rank Space Captures Linear Alignment Between LLM and Human Neural Activity During Naturalistic Language Listening
Large language models (LLMs) are increasingly used as computational models of human language processing, yet it remains unclear which components of their representations drive alignment with neural…How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
Safety alignment for Large Language Models is heavily focused on English with limited multilingual representation, particularly damaging low-resource language performance.