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 125
EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents
Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on the user simulator and environment, which jointly…Support or Magnitude? Characterizing Neuron Relevance for Instruction Data Selection
Model-internal signals, such as neuron activations and gradients, have been used for instruction data selection, yet how neuron relevance should be characterized remains underexplored.Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards
Reinforcement learning with verifiable rewards (RLVR) is reshaping how large language models (LLMs) acquire reasoning capabilities, yet the optimizers used remain largely inherited from…PatTransBench: an ipc-stratified, multi-dimensional benchmark for patent machine translation evaluation
We present PatTransBench, a 12,000-item Chinese-English/Japanese/Korean patent machine translation (PatMT) benchmark with a four-dimensional evaluation protocol.Know Yourself and Know Your Neighbour: A Syntactically Informed Self-Supervised Compositional Sentence Representation Learning Framework using a Recursive Hypernetwork
Sentence representation learning is still an open challenge in Natural Language Processing.MixLID: Token-Level Language Identification in Mixed-Language Text
Processing multilingual text requires both identifying a broad range of languages and distinguishing the language of each token in inputs containing multiple languages.SuPER-Mamba: Surprisal Prioritization for Extended-Context Routing in Mamba
State space models provide efficient linear-complexity processing for long sequences, but their performance frequently degrades as context length grows.SIREN: Situation-aware Index for Response and Emergency ActioNability in Crisis Translation
Machine translation (MT) is increasingly utilized in multilingual crisis communication, yet conventional evaluation does not directly assess whether translated emergency messages preserve their…Does a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev
Decision APIs that return a probability for each option are routinely used as if those probabilities were properties of the options themselves.EHR-Bench: A Chinese Multi-Task Benchmark for Recruitment AI
Recruitment applications span diverse operations, from drafting job descriptions and interpreting queries to organizing profiles, assessing fit, and recommending candidates and jobs.Attention-Graph Curvature for the Verification of Mathematical Reasoning
Language models have recently solved open Erdős problems and achieved gold-medal level performance on International Mathematical Olympiad problems.Audit Before You Distill: A Controlled Workflow for Reasoning Transfer into Compact Medical Language Models
Teacher rationales can help a smaller model answer health professions questions, but they can also reinforce errors.Where Is the "Self" of a Large Language Model? -- From Self-Index to Self-Reference
Does a large language model have a self, and if so, of what kind?Learn from Move: the Next Step for GUI Agents
Existing benchmarks for GUI agents primarily focus on increasing task difficulty by extending task horizons.Lost in Contrast: Instruction-Preserving Decoding for Reliable Visual Question Answering
Visual contrastive decoding corrects answers using the prediction difference between the original image and a reference condition, yet the same contrast also turns supported abstentions into…The Multilingual Artificial Hivemind: Do All LLMs Think Alike in Every Language?
Text generated by Large Language Models (LLMs) often remains limited in diversity compared to that produced by humans.Is the Platform Part of the Measurement? A Protocol and Simulation Study for Cross-Platform Equivalence of Machine-Labelled Policy Sentiment
Comparing machine-labelled sentiment across social media platforms is now routine: differences in classifier scores between platforms are read as differences in public opinion.A Bethe-Ansatz Source of Early Token Correlations: A marginal-preserving construction for parallel proposals
Parallel token proposals need a joint law, not merely accurate token marginals.TPPO: Tracking-Value PPO For Language Model Reasoning
Proximal Policy Optimization (PPO) is widely used in reinforcement learning with verifiable rewards for language-model reasoning.The Bell Boundary of Shared Representations
When does a shared representation become insufficient for jointly supporting multiple tasks?