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 128
Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning
Language models are often evaluated alone but increasingly deployed together, routed between, made to debate, ensembled, or collaboratively trained.Distilling Text LMs into Speech-to-Speech LMs by Matching Internal Text Predictions
Text language models (LMs) acquire broad linguistic and factual capabilities through large-scale pretraining, while comparable capabilities remain difficult to learn from speech alone.Scaling Inference-Time Compute with Teams of Coding Agents
Multi-agent systems promise a new axis for scaling inference: rather than having one agent think longer or sample more attempts, a task is split across many agents that work in parallel and…A Sense of Proprioception in Language Models
In humans, proprioception corresponds to the sense of self-movement or position, e.g. understanding the position of one's arm.Does Personalization Break Trust? Open-Set Rejection Calibration Under Few-Shot On-Device Intent Adaptation
Always-on virtual assistants increasingly personalize on-device to new user-specific commands via few-shot fine-tuning (e.g., LoRA), but this adaptation is evaluated almost exclusively on whether it…Sequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning
We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them.Do correct answers have stable latent knowledge support?
Large language models are typically evaluated in terms of the correctness of their output.North or South? Diagnosing LLMs' Understanding of North Korean Language, Society, and Knowledge
Large Language Models (LLMs) have made substantial progress in multilingual question answering, yet their ability to understand low-resource sociolinguistic contexts remains under-explored.A Sovereign, Indic-First, Reasoning Model
Gnani-Evon-v3.3-30B-A3B is a long-context hybrid Mamba-Transformer mixture-of-experts model for reasoning, instruction following, and tool use in English and eight Indian languages.In-Place Indic Tokenizer Expansion and Continual Pretraining of Nemotron-3-Nano-30B-A3B
We adapted Nemotron-3-Nano-30B-A3B for eight Indian languages without changing its backbone architecture.From Candidate Tokens to Final Outcomes: Decoding Relative Long-Horizon Candidate Value from Reasoning Model Representations
Large reasoning models generate reasoning trajectories token by token.Sensitivity or Criterion? Measuring and Moving When Language Models Act
Before an agent acts, it must decide whether action is warranted.Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play
Despite significant advances in language understanding, Large Language Models (LLMs) can still miss meaning hidden in plain sight, failing to identify harmful intent in expressions readily…AlphaPilot: Multi-Turn Tool-Using LLM Agents for Adaptive Alpha Mining with Reinforcement Learning
Formulaic alpha mining seeks interpretable expressions that rank assets by future returns.Concept Representations in Vector Space: Quantifying Sharedness and Idiosyncrasy of Meaning
Concepts are the basic units through which we navigate the world and communicate meaning.REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming
Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training.SARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning
Structured pruning reduces the inference cost of large language models (LLMs) by permanently removing neurons and weight rows, yielding dense, hardware-agnostic speedup.A Step in the Right Place: Understanding and Optimizing Timestep Placement in Continuous Diffusion Language Models
Continuous diffusion language models represent an emerging paradigm for language modeling.Apertus 1.5: From Open Text Models to Open Multimodal Reasoners
Language models are becoming infrastructure, and infrastructure built in the open, by public institutions, on documented data, is the alternative to dependence on a few providers; Apertus shows this…An Interpretable Linguistically-Grounded Analysis of Scene Saliency in Movie Screenplays
We investigate the factors affecting salience in movie screenplay by posing two research questions: 1. {\em Does Uniform Information Density (UID) predict salient scenes?} 2. {\em What other…