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 150
Input-Blind Controls Produce Substantial Oracle Headroom for Layer Programs in Multiple-Choice Evaluation
Adaptive computation aims to improve language-model inference by tailoring execution to each input.Document-Level Text Simplification in Estonian Using Large Language Models
Document-level text simplification involves transformations that go beyond sentence-internal edits, addressing discourse coherence, anaphora resolution, and cross-paragraph consistency.Reasoning-Token Spikes Under Prompted Untruthful Responses in Large Language Models
Monitoring the chain-of-thought of reasoning artificial intelligence (AI) models remains a key approach to detecting deception and other forms of misbehavior in such models.Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds
Speculative decoding accelerates large language model inference by using a low-cost draft model to propose tokens that the full-size target model verifies in parallel.Which Rollout Taught It That? BehaviorTrace and the Limits of Training-Data Attribution in Online RL
When reinforcement learning teaches a language model a new behavior, can we find the training rollouts that taught it?CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution
Terminal-agent capability depends jointly on model weights and the runtime harness that formats prompts, binds tools, and handles error recovery.RunningTab: Direct Workspace Interaction with Environment-Side Tabs
Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over.PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
Hallucinated information can propagate through multi-stage LLM systems and become part of the context for subsequent reasoning.Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models
Many of the questions now put to large language models have no correct answer to score against: what a policy is worth, which option a user should choose, how to weigh competing values.Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding Models
Prompted embedding models have recently received increasing attention, particularly for retrieval, where detailed retrieval instructions are provided as part of the retrieval prompt.Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-language models they are built on.EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory
Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation.Decoupling Exploration from Optimization in RLVR
Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints.WorldBench: Evaluating LLMs on Three.js Voxel World Generation
Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable.Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models
Looped Language Models (LoopLMs) offer a parameter efficient approach to scaling reasoning by reusing shared parameters across recurrent computation steps.Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System
Work zones are critical yet hazardous components of transportation infrastructure, requiring carefully designed Transportation Management Plans (TMPs) to ensure safety and mobility.Cognitive Thermometers: Machine Learning and Logical Complexity
How does the human mind represent semantic categories?Lossy Compressive Text Autoencoders
Our work explores learning a compressed latent representation of text, at the intersection of data compression and representation learning.Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training
Conversational task disambiguation over tabular data uses dialogue to resolve missing information about a user's intended task before producing a solution over tables or databases.Clarify, Then Focus: Statement Normalization for Conversation Analytics at Scale
Enterprise conversation analytics asks many questions of millions of interactions.