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 58
Where meanings converge and diverge: Revisiting linguistic relativity across 81 languages
Do people who speak different languages organize concepts in similar ways?MixJudge: Learning a Language-Queryable Critic for Vocal Mixing
Mixing requires not only applying processing but also assessing the resulting mix.Invisibilization as a Source of Probability Bias in Language Models
Language models are aligned to avoid using protected attributes such as race, ethnicity, and gender to inform their responses.TutorCaseBench: A Case-Grounded Benchmark for Evaluating LLM Tutors in Supporting Students with Challenging Behaviors
LLMs are increasingly used as AI tutors, yet existing benchmarks overlook the challenging behaviors common among students with learning and behavioral difficulties.TRIAD: Benchmarking Omni-Modal Ambiguity in Multimodal Large Language Models
Ambiguity is a central feature of natural communication: a sentence, image, or sound may remain underspecified until evidence from the other channels is considered.Synthetic-to-Real Code-Switched ASR: A Spontaneous Nepali-English Podcast Benchmark
Nepali-English code-switched conversational speech presents severe challenges for automatic speech recognition (ASR), chiefly through script confusion (inappropriate mixing of Devanagari and Latin…One Teacher, Many Views: Reducing Reference Sensitivity in On-Policy Self-Distillation
On-policy self-distillation (OPSD) improves reasoning by training a model on its own trajectories with dense token-level supervision from a privileged copy conditioned on a reference solution.Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models
Reinforcement learning (RL) is credited with teaching reasoning models to write {wait} before reconsidering a step, yet large RL accuracy gains do not require the word.From Perpetrators' Digital Footprints to Behavioral Communities: An Ontology-Driven Framework for Bengali Cyberbullying Analysis--- FULL VERSION
Cyberbullying involves behavioral and contextual patterns beyond isolated abusive messages.Silicon Samples Match the Answers but Not the Respondents
Silicon sampling generates survey respondents by having a large language model (LLM) answer a survey as a person with given demographic attributes, and the resulting synthetic populations are…Hierarchical Fine-Grained Cross-Modal Alignment via Dynamic Granularity Discovery and Optimal Transport
Fine-grained image-text retrieval requires a model not only to assess global semantic consistency between an image and a text, but also to model visual evidence for local textual semantics…ReflectPO: Reflection-Guided Policy Optimization for Long-Horizon LLM Agents
With external tools, large language models (LLMs) can tackle complex tasks through sustained environmental interaction.Verbalizing Activation Differences with Natural Language Autoencoders
Activation verbalizers translate the internal representations of large language models into human-readable text.Tracing Hallucinations in LLM Reasoning for UML Class Diagram Generation: An Empirical Taxonomy and Mitigation Study
Large Language Models (LLMs) can generate UML class diagrams from natural language requirements, but hallucinations may compromise the correctness and completeness of the resulting diagrams.RetiJev: Fast and Source-Grounded Ophthalmic Decision Models
Ophthalmic clinical decision support requires fast, accurate, and privacy-preserving inference, yet autoregressive large language models (LLMs) incur substantial latency and computational overhead…IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated).Once a Tree, Always a Tree? Cross-lingual Transfer of Hierarchical Generalization in Language Models
Language models (LMs) often exhibit successful cross-lingual transfer through continued (pre)training, still their underlying process remains unclear.Joint or Per-Option? Compact Encoders for Closed-Set Decisions from 17 Million to 1 Billion Parameters
Many language-model pipelines end in a closed-set decision, such as selecting a tool.A Reality Check of Inference-Time Context Augmentation Methods
Large language models (LLMs) often fail to utilise the context given in the input, resulting in hallucinations or a fallback to parametric knowledge.Interpretive Variation and Discourse Structure in Detecting Enthymemes in Controversial Political Discourse
Enthymemes are arguments that leave a premise or conclusion unstated, and they are a common persuasion device on social media.