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 6
AssameseLM-E2B: An Open-Weight Assamese Language Model for Efficient Consumer-Grade Deployment
While Large Language Models (LLMs) excel in high-resource languages, their performance often degrades in low-resource languages due to tokenization inefficiencies, generative instability, and…Editing Large Language Models with Geometry-Aware Regularization
Knowledge editing has become a key technique for updating knowledge in large language models.Loop Before You Leap: What Recurrent Depth Can and Cannot Buy in Data-Limited Pretraining
Multimodal models have often scored below text-only baselines in the BabyLM Challenge (Klerings et al., 2024; Takmaz et al., 2025).Zuse: A Decision Model for European Languages
Decision models read a document and return a probability for each of a fixed set of options instead of generating text.Mass Producing Training Data with Surprising Side Effects
Training data can have unexpected side effects on language model behavior outside the training domain: insecure code data can induce broad misalignment, and outdated bird names can induce a…Training-Free Character-Length Control in Summarization with Diffusion Language Models
Summarization with a fixed character length is important for tasks such as headline and article preview generation, where text must fit an exact space.Corralling AI Risks with Grassroots Contracts
AI's inflection point is a fountain of alarming risks.Does Context Compression Preserve Refusal Alignment?
Context compression reduces inference cost by encoding inputs into compact representations while preserving semantic content.LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution
As LLM-based agents develop, they have been increasingly applied in the legal domain.Presentation Sensitivity in Typed Decision Models for Subjective Text Evaluation
Typed decision models offer structured choices, scores, and probabilities for low-cost automated evaluation.Where Should a KV-Cache Repair Budget Go? Distractor Structure and Contextual Compatibility in Non-Prefix Reuse
Non-prefix KV-cache reuse encodes retrieved chunks independently and concatenates their caches.Interpretable Text Embeddings Based on Hierarchical Questions
QA-based text embeddings represent texts as vectors consisting of 1/0 answers to yes/no questions.Ruby-OPD: Enhancing Pronunciation Controllability and Accuracy for Flow-Matching Text-to-Speech via On-Policy Distillation
Achieving both high pronunciation accuracy and fine-grained controllability remains a central challenge in Japanese text-to-speech (TTS), as Japanese is an unsegmented language mixing logographic…Twists and Turns: A Graph-Based Benchmark and Framework for Long-Term Memory in Exploration Tasks
Long-term problem-solving processes, such as scientific research and software development, proceed along an evolving trial-and-error trajectory toward a central goal.EvoGuard: Mitigating Degradation in Online Skill Evolution
Skills let language agents reuse experience across tasks as natural-language documents.ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs
Graph-based retrieval-augmented generation (GraphRAG) answers questions by retrieving over a knowledge graph built from a corpus.What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?
While multi-turn agentic reinforcement learning (RL) excels on long-horizon tasks, its performance gains remain highly sensitive to interaction constraints.LibriSpeech-Real-QA: A Benchmark for Streaming Question Answering
Most speech large language models (SLMs) still process speech in an offline manner.CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation
Simultaneous Speech Translation (SimulST) requires balancing translation quality and latency.NaijaFacts: A Framework for Disentangling Language from Knowledge in Facts about Nigeria
Multilingual benchmarks for African languages mostly translate generic questions into local languages, measuring linguistic competence but not whether models know facts about Africa.