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 111
Scaling Multilingual Mixture-of-Experts: How Language Coverage Changes Capacity and Compute Allocation
Multilingual models share capacity across languages, so adding languages can hurt performance on existing ones.Repairing Speech Access After Text Updates with Frozen Affine Fields
Speech-capable language models inherit most of their knowledge from text-rich language backbones, and continued model maintenance is likewise dominated by text updates.Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian Languages
Every multilingual speech pipeline begins with a language decision, an error there propagates silently through recognition, translation and routing.CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing
Large language models (LLMs) have demonstrated multilingual capabilities across diverse language generation and understanding tasks.Neural POS Tagging for the Low-Resource Saraiki
Part-of-speech tagging is a fundamental sequence labeling task and an important component for many downstream natural language processing applications.Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded Inference
Reliable medical reasoning requires LLMs to dynamically access external biomedical evidence to improve factual trustworthiness and reasoning accuracy.MMLA-RSI: Recursive Self-Improvement through RTT and RTMA
An agent can improve its behavior within an unresolved problem by changing how it acts and which experience it retains.Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages
India's 22 scheduled languages are spoken by over a billion people in conversations that mix languages, often within one turn, overlap freely, and take place over telephones, in meetings, and in…TreeFlex: Agents Navigating Their Own Search Trees
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context.Do AI Agents Gossip? Evaluative Talk in Human and AI-Agent Online Communities
Gossip, defined as evaluative talk about absent third parties, is widely seen as a uniquely human social practice.Lexical Persistence Without Semantic Entrenchment in AI Agent Communities
AI agent communities sustain lexical persistence, popular terms spread, recur, and achieve broad adoption, but whether they also develop the temporal semantic structure characteristic of human…Cascaded Retrieval with Cross-Modal Query Refinement for Efficient Visual Document Search
Retrieving information from visually rich documents requires matching queries against pages that contain complex evidence in tables, figures, and layout-dependent structures.From Triage to Impact: A Multi-Hop Reasoning Benchmark for Explainable Persian Hate Speech
Hate speech has become increasingly prevalent on social media, raising concerns about its detection, interpretation, and moderation.FOLD: Position-Free Far Memory with Local Order for Long-Context Speculative Decoding
Speculative decoding accelerates LLM generation through lightweight drafting and parallel verification.Cortex: Consolidating Context into Parametric Memory
Context can improve large language model performance, but these gains may be lost after context removal.From Unreliable to Usable: Decomposing Failure Modes and Confidence Signals in LLM Entity Extraction - Evidence from Cyber Threat Intelligence
Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures actually consist of, and whether confidence…Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks
Retrieval-Augmented Generation (RAG) models have become almost a cornerstone of open-domain question answering tasks; in which the quality of answers generated in the process, greatly relies on the…SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm
Recursive self-improvement (RSI) in scientific research aims to improve agents' research capabilities through their own experimental experience.The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation
The scaling relationship of compute and performance for language models (LMs) has been extensively studied; more recently, models are being designed to scale memory use, as well.Same Claim, Different Interpretations: How LLM Agents Resolve Ambiguity in Scientific Claims
Co-scientists and agentic scientific claim verifiers are increasingly used to assess claims across the sciences.