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 33
FARO: Function-Space Adaptive Return-to-Risk Optimization via Cross-Block Equal-Risk-Contribution Budget Allocation
Training a large language model is compute-bound, and current recipes divide the work between optimizers by hand: orthogonalized momentum for attention and MLP matrices, Adam-style updates for the…Incongruence-Aware Evaluation of Multimodal Speech Emotion Recognition in Audio Large Language Models
Voice-interactive large language models process both what a speaker says and how they say it, yet the two channels do not always agree.Qistas: A Pre-Registered, Portable Protocol for Fairness Evaluation of Large Language Models
Fairness benchmarks for large language models (LLMs) are overwhelmingly English-born and American in their social categories; translated versions carry those categories into societies where they do…CoFiBreak: A Coarse-to-Fine Diversity Reward for Effective Multi-Turn Jailbreak
Automated red teaming trains an attacker large language model (LLM) to elicit harmful responses from a victim LLM, but reinforcement learning can collapse attackers onto a narrow set of prompts when…Agentic World Modeling for Agent Test-time Scaling without Environment Replica
Test-time scaling (TTS) improves large language model agents by sampling and selecting among multiple candidate trajectories, but common realizations assume that these trajectories can be executed…Adaptive Personalization Under Preference Epistemic Uncertainty
Human preferences change over time: an established preference may remain valid over time, become uncertain as context shifts, or be explicitly revised.Kernel-based Interpolatory Methods for Context Compression of Attention Mechanisms
The bottleneck of attention mechanisms, which are the fundamental building block of modern language models, is their quadratic complexity in terms of context size.Better Retrievers, Worse Labels: How Incomplete Relevance Judgments Distort Abstention Evaluation in Conversational RAG
Conversational RAG benchmarks such as MTRAG and RETECO evaluate retrieval and generation end to end: each system answers from its own retrieval, so abstention must be scored against whether each…Nedimo: An Evidence-Grounded Multilingual Pipeline for AI-Generated Sleep Stories
Generative audio systems can produce large libraries of personalized bedtime content, but ordinary media objectives (retention, completion, and novelty) are poorly aligned with the goal of…Fewer Heads, Fewer Memories: Pruning Redundant Attention Heads Suppresses Verbatim Memorisation
Large language models have been shown to memorise and reproduce verbatim sequences from their training data, raising concerns about privacy leakage, intellectual property exposure, and the limits of…The psychophysics of affect in large language models
Good decisions often require considering how outcomes will feel.Do Open Language Models Invent Scripture? BILAL-BENCH: Benchmarking Islamic-Source Fabrication in Bengali
When a language model invents a Qur'anic verse or hadith, it gives false authority to text that readers may treat as sacred.MOSAIC: Addressing Disproportionate Task-Modality Dependencies via Modality-Partitioned Gradient Routing
In multi-task settings, combining multiple modalities allows task representations to draw on signals that a single modality alone would not capture.Language Models Show Conformity Bias in RAG: When the Majority Endorses a Poisoned Claim
Retrieval-augmented generation (RAG) can expose language models to misleading evidence in retrieved documents.Do Language Models Know What Compelling Scientific Evidence Looks Like?
Expert scientists excel at weighing empirical findings from multiple sources that vary in both statistical reliability and epistemic relevance.Capability-Grounded Agentic Planning
LLM agents serve natural-language requests through tools, data sources, and other agents, and even simple requests often need several interdependent calls.EDU-Jev Training System-One Decision Models for Education
Many automated decisions in education involve choosing from a fixed set of options: assigning a rubric score, checking whether an answer meets a marking criterion, or identifying the first wrong…Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI
We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic…Calculation and rejection diverge in language models tested at known mechanical limits
When a language model returns engineering quantities with the status "solved", software that trusts it passes them on, even when the requested design is physically impossible.ATI-OPD: Adaptive Teacher Intervention for Stable Long-Sequence On-Policy Distillation
On-policy distillation (OPD) trains a student on its own responses using token-level feedback from a teacher.