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 117
SparPR: Runtime KV-Cache Recovery for Resource-Constrained LLM Inference on Consumer Hardware
Running large language models (LLMs) on consumer hardware is bottlenecked by the key-value (KV) cache, which grows with every decoded token and quickly exhausts the memory and bandwidth of a single…Attacking Only Half the Data: Two-Sided Evaluation of AI-Text Detector Robustness
We investigate the robustness of widely used AI text detectors under attacks applied to both human and machine text.Fan Out or Relay? Ownership-Aware Routing for LLM Agents Querying Siloed Tables
Inside organizations, a question's data often sit with several owners, who query their own tables but never hand them over.Claim Framing as a Driver of LLM Sycophancy
Sycophancy in Large Language Models, the tendency to align responses with user preferences over ground truth, has largely been studied using questions without a clear ground truth and with a single…LoOPSD: On-Policy Self-Distillation with Looped Teachers
On-policy self-distillation improves a model using guidance from the model itself, but it still requires a teacher that provides more useful predictions than the student.TRACESTEER: Trace Driven Activation Steering for Hallucination Mitigation in Diffusion Language Models
Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive LLMs, yet remain susceptible to hallucination.SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents
We present SWE-MISBEHAVIOR, the first taxonomy and evaluation framework for diagnosing boundary-violating misbehaviors in coding agents.TextualRL: Textual Reinforcement Learning for Context Management
LLM agents can adapt to task feedback by revising the textual context that guides their behavior, without changing their model parameters.Consider, Then Choose: Order-Invariant Decisions in System One Models
System One models answer typed questions in a single forward pass and promise the same answer for the same input.PACT: A Pragmatic Prompting Framework for Expressive and Voice-Preserving Speech-to-Speech Translation
Speech-to-speech translation should preserve not only what is said, but also who says it and how it is said.Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models
Benchmarks are essential for evaluating and improving large language models (LLMs).Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Third-party skills can expose LLM agents to malicious instructions hidden by encoding.PAINT: A Framework for Multilingual Pain Representation from Medical Licensing Exams to Real-World Clinical Texts
Pain is one of the most common and clinically important symptoms, reflecting disease onset, progression, and treatment response.JevGPT: Thinking Fast and Slow in Autonomous Research
Autonomous research agents must acquire and reason over evidence within a limited budget.LegalRewardBench: Benchmarking Reward Models for Legal Preference Evaluation
Reward models are central to preference alignment for legal tasks, yet existing reward model benchmarks are still primarily centered on general-domain preferences.SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems
Conversational Recommender Systems (CRSs) require reliable user simulators for cost-effective evaluation.Prompt or Policy? Optimizing Physician Slate Presentations with LLM User Simulators
Choosing the right physician is a key challenge for patients seeking medical care.Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees
Agent harnesses require a low-latency guardrail model together with customizable audit policies.Probing the Geometry of Color Representations in Multilingual Language Models
Do multilingual language models learn a universal internal geometry for color, and is it perceptually grounded or primarily linguistic?Lightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, and English
Post-training quantisation reduces the memory cost of large language models, but it remains unclear whether compression preserves language skills of regional varieties as reliably as their…