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 161
Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory
While modern large language models (LLMs) have been trained to reason through verbalized chains-of-thought, the generation cost grows substantially due to suboptimal paths to reach the final answer.Anatomy of LLM Sycophancy: What a Flip Rate Hides
A model under pushback can correct itself, capitulate, or hold, and one flip rate counts a correction and a capitulation alike.Synthetic Cultural Agents from Aggregate Anchors
Population prompts are widely used to generate synthetic survey responses, but they combine information supplied at inference with associations already encoded during pretraining.Before Agent Tells The Lie: Has Deception Already Been Represented?
Large language model (LLM)-based agents can exhibit deceptive behavior during task execution, including hiding failures, fabricating results, or falsely signaling task completion.Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control
World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay, packet loss…Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants
AI voice assistants often use Automatic Speech Recognition (ASR) with LLM-based reasoning, yet existing systems struggle with regional British accents, including Scottish, Irish, and Welsh accents…Molecules of a Story: Community Detection in PMI-weighted Narrative Networks
Automatically extracted narrative networks -- graphs with entities as nodes and their relations as edges -- have proven useful for revealing central narrative structures through salient entities and…Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models
Text from multiple sources can become interleaved into a single sequence when attribution metadata is lost, such as overlapping speech transcripts, document reading flows, or concurrent agent streams.COMPASS 2.0: psychometric representational similarity analysis distinguishes symptom structure from personal signal
Language models can score psychiatric questionnaires from speech, but agreement with self-report may reflect the questionnaire rather than the person.Frozen Factor or Spectral Band? Disentangling Two Choices in Low-Rank LoRA
Spectral variants of low-rank adaptation (LoRA) choose both a subspace and which factor to freeze.JEV versus LLMs: Accuracy, Cost and Calibration on Seven Political Science Replications
Large language models (LLMs) annotate and scale political text or constructs by generating text tokens.Long-Horizon Textual World Modeling through Structured Reasoning
World models must predict how an environment evolves under sequences of actions, enabling agents to compare possible futures and reason about counterfactual actions before acting.LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches
Reinforcement learning has greatly advanced the capabilities of large language models, but its memory demands remain a barrier to broader adoption.Representation-Space MMD for Diffusion Language Models
We introduce a post-training method for diffusion language models (DLMs) that minimizes Maximum Mean Discrepancy (MMD) between generated and reference distributions in the feature space of a frozen…Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents
Wikidata is one of the largest open knowledge bases, yet answering a complex question over it still requires a SPARQL query that names the right entities and properties and chains their relations.What Matters for Latent Reasoning with Flow Matching
Latent reasoning lets a large language model (LLM) think in a continuous space and verbalize only the answer.Language models can notice an impossible engineering problem yet still report it as solved
Language models draft engineering calculations, but answer accuracy does not show whether they reject an impossible problem.Reward Stealing Attack on Large Language Models
Adversarial attacks on Large Language Models (LLMs) aim to induce harmful content.The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance
Are language models compliant with user instructions?How Sparse Probability Maps Shape Mixture-of-Experts Routing
Mixture-of-experts (MoE) routers typically apply softmax to the router scores and keep the top-K experts, making every token use exactly K experts.