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 163
Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine
Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool calling, and fine-tuning them needs per-API data…Smart Content Ingestion for Generative AI Workloads
The evolution of machine learning has progressively changed where intelligence resides in an AI system.JudgeMoE: Distributional Aggregation for LLM-as-a-Judge
When an LLM judge scores an output, its score distribution retains uncertainty and disagreement information that is lost after scalar compression.Jailbreaking Open-Weight LLMs via Random Embedding Perturbations
While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important concern.CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets
Croissant has emerged as a standard for machine-readable dataset metadata, yet populating its fields remains labor-intensive and requires careful reading of accompanying dataset documentation.A theory of platonic representations in language models
Representations of translated sentences are similar in the inner layers of multilingual language models -- an observation connected to the platonic representation hypothesis, yet unexplained…CLM-as-a-Judge: Evaluating an Open Contrastive Decision Model on Public Judge Benchmarks
An open contrastive decision model is near chance as a judge on the hard public benchmarks: Contrastive-LM/CLM-v0.1-8B scores between 0.351 (best- of-four, chance 0.250) and 0.593 (pairwise, chance…Learning Scientific Exploration from Human Research Decision Trajectories
A key challenge in building AI systems for scientific research is enabling $\textit{scientific exploration}$: the systematic process of investigating unknown phenomena or ideas to gain new knowledge…Identifying Introspection From the Inside
Large language models make claims about themselves that are both consequential and increasingly difficult to verify from behavior alone.Responsible Institutional Analytics: Interpreting Bias with AI Support
Institutional Analytics (IA) dashboards inform decision-making in higher education, yet data limitations, constraints in analytical techniques, and missing contextual information often affect their…Forecasting the Growth of Social Media Information Cascades: Towards Human-in-the-Loop Misinformation Triage
Limited review teams must identify which emerging claims are likely to keep growing before their eventual reach is known.TIDE 2.0: an open, model-agnostic engine for keyed de-identification of clinical notes
Clinical notes capture most of what is documented about a patient's care, but they cannot be used for research until protected health information (PHI) is removed.Minimal Witness Reinforcement Learning
``What are the irreducible conditions that are sufficient to produce an outcome?'' is one of the most common questions that recur across computation and science.Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents
Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester could not derive, and departments can silently…Kurate: Scalable Scientific Quality Analysis
Scientific search systems can find papers that are relevant to a question, but they generally do not assess the quality of the evidence that those papers provide.SharedKV-BT: Node-Local Typed Decisions for Behavior-Tree Agents
Agent tasks require sequences of interdependent decisions.Structuring MoE Expert Selection for Agentic Reinforcement Learning
Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of agentic behavior and MoE structures remains underexplored.Logbook: Extremely Long-form Audio Event Understanding
Audio benchmarks are built around short, pre-segmented clips, limiting model design to brief inputs or fixed vocabularies.A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care
Tactical Combat Casualty Care (TC3) requires responders to connect visual observations of injuries and interventions with established clinical guidance.Stepped MoE: Segment-Level Routing with Configurable Inference Complexity
Training large language models (LLMs) is resource-intensive, and adapting them for diverse deployment scenarios with varying computational constraints remains challenging.