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 18 September 2026 to 6 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 216
InfoEdit: Probing Global Layout Reasoning in Infographic Editing
Multimodal foundation models edit natural photographs at production quality, yet the same models struggle with structured visual content such as infographics.Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models
Reinforcement learning with binary correctness rewards trains correctness, not calibrated confidence.TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces
An agent can complete a task while exhibiting undesirable behavior during execution.BaatCheet: A Multilingual Corpus for Dialogue Translation in Indian Languages
Existing translation models are typically trained on sentence-level and formal text, limiting their ability to capture everyday conversational dialogue phenomena such as informality, speaker…Hesitation-Aware On-Policy Distillation for Diffusion Language Models
Diffusion large language models (dLLMs) generate text by iterative unmasking.Robust Hierarchical Structures for Agentic Document Analysis
Large Language Models (LLMs) enable us to better understand text documents, including PDFs and Word documents.CertMark: Distortion-Free Multi-Bit Watermarking with Certified Decoding
Leading multi-bit watermarking methods for language models encode messages by biasing the model's next-token probabilities, creating a trade-off between message recovery and text quality.When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression
Training-free KV-cache compression methods such as SnapKV, H2O, and PyramidKV evict tokens at the end of prefill, aiming to preserve the attention mass that future queries are expected to use…Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training
Predicting how an environment will change before acting is a natural route to better decision making for agents.CalibHyper: Chance-Corrected Relational Hypergraphs for Few-Shot Molecular Property Prediction
Molecular property prediction is central to drug development and materials discovery, but experiments are costly and labeled data are scarce.CHI: A Composite Hallucination Index Unifying Entity, Relation, and Quantity Dimensions for Summarization Evaluation
Faithfulness evaluation of abstractive summaries remains an open challenge, with existing metrics addressing only isolated hallucination types: factual entity errors, relational inconsistencies, or…Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models.From Script to Drama: An Agentic Framework for Controllable Multi-Speaker Dialogue TTS
Multi-speaker dialogue TTS requires natural speech generation, consistent speaker identity, coherent cross-turn transitions, and fine-grained control of expressive attributes such as emotion…NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents
Large language model agents increasingly rely on compound programs for retrieval, tool use, reasoning, and verification, yet their failures often arise from local procedural decisions.OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading
Semi-autoregressive diffusion large language models (dLLMs) improve decoding parallelism through iterative block-wise denoising, but scaling them with mixture-of-experts (MoE) layers introduces a…From Position Risks to Block Survival: Faster Generation for Diffusion Language Models
Diffusion language models (DLMs) can accelerate generation by predicting multiple tokens in parallel, but there is a mismatch between how these tokens are predicted and how they ultimately…Preserving Morphemes: Morphology-Guided Pre-Tokenization for Nepali
A byte-level BPE vocabulary learns each inflected form of a Nepali word as a separate string, so a noun stem is spelled differently in each of its case-marked forms.Decoupling Token Roles in Autoregressive Pretraining
Autoregressive pretraining increasingly draws on heterogeneous data, making it important to understand how a model learns from an individual token.Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation
On-policy distillation (OPD) transfers the capabilities of a large language model to a smaller student by providing teacher supervision on the student's own rollouts.MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses
Rapid progress in Large Language Models (LLMs) is saturating static benchmarks faster than they can be designed.