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 130
An Explainable System for Offensive Content Detection in Nastaliq Urdu: Corpus Curation, Transformer Benchmarking, and Word-Level Attribution
Automated moderation systems are deployed at scale, yet they remain opaque to the users and moderators affected by their decisions, and their coverage is almost entirely confined to English.Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning
The introduction of long chain-of-thought (CoT) reasoning and external tools has substantially improved the performance of multimodal large language models (MLLMs) on general and reasoning tasks.Local Citation Recommendation Without Graph Signals
Resolving correct citations can be a time-consuming task for research writers.Latent Taxonomies: How Property Induction Develops in Language Model Pre-training
When told that robins have sesamoid bones, people are far more prone to extend the property to sparrows than to whales.KhyontekAI at CheckThat! 2026: Multilingual Dense Retrieval and Cross-Encoder Reranking for Scientific Web Claims
Scientific claims shared through social media platforms frequently reference research findings without explicitly linking to the corresponding scientific publications.Binding Phoneme Identity to Position in Neural Models and the Human Brain
A fundamental challenge in cognitive science and neural computation is the binding problem.What Do Sparse Autoencoder Feature Discovery Scores Identify? From Activations to Interventions
Sparse autoencoder (SAE) features are typically discovered from how their activations co-vary with behaviour, yet they are often used through interventions such as steering or ablation.Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction
Large-scale personalization is shifting from embedding-table retrieval to LLM-based recommenders that generate the Semantic ID (SID) of the item to recommend, where each SID is a short sequence of…Unchecked or Falsely Accused? Evaluating AI-Generated Text Detectors on Kazakh
AI-text detectors are already applied to Kazakh writing, yet no study reports how often publicly available detectors flag Kazakh text whose human authorship is dated before ChatGPT.Review Rarely Beats the Stronger Model: Separating Verification from Capability Transfer in LLM Pipelines
Qwen3-8B reviewing Llama-3.1-8B in math adds 33.2 points, yet Qwen3-8B alone is 6.4 points more accurate than the result.RIVO: Lightweight Adaptive Rerouting for Deep Research Agents
Deep Research agents rely on long-horizon reasoning and iterative tool use to solve complex information-seeking tasks.More Reasoning Is Not Always Better: Executing Clinical Guidelines with LLMs and Rules
Large language models (LLMs) have shown considerable promise in clinical decision support.The Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much
Evaluation of text generated by large language models (LLMs) is increasingly delegated to LLMs acting as judges, yet what such a judge must be shown remains unresolved.Natural Language Processing for Aligning Readings with Learning Objectives and Assessing Topic Balance in Dental Education
Curriculum teams often lack time to check whether assigned readings support learning objectives (LOs) and whether topic coverage is balanced.Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment
Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones.Scaling Repeated-Data Pretraining: Batch Size, Regularization, and GPU-Time Tradeoffs
We study pretraining when compute is abundant but unique training data are finite, requiring repeated training on the same data.Mixed Feelings, Single Polarity
Emotion datasets are routinely mapped onto positive and negative valence, by assigning each emotion category one polarity.Scaling Laws for Multimodal Data Mixtures
Frontier AI systems are increasingly natively multimodal, jointly pretrained on multiple modalities, such as text, vision, and audio.MemForm: Benchmarking Memory Formation Poisoning in LLM Agents
Long-term memory enables LLM agents to learn from past interactions but exposes memory formation to adversarial influence.Neither True nor False: Do LLMs Represent Truth-Value Gaps in Plural Predication?
Do Large Language Models (LLMs) genuinely grasp the truth conditions of plural descriptions, or do they force every sentence into true or false?