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 152
LOGIC: An LLM Benchmark for Intent-Grounded Change Impact in Aerospace Electrical Systems
Aerospace electrical-design revisions can contain multiple genuine changes, although an engineering request may authorize only a subset.Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference
LLM orchestration investigates how an orchestrator coordinates a group of autonomous agents to achieve common goals or maximize collective welfare.Recurrent Looped Transformer
State tracking requires an update at every input, but the depth a Transformer applies to each token is fixed regardless of sequence length.Stateless Language Agents: Scaling Long-Horizon Automated Research
Automated research systems increasingly run LLM agents over long horizons, but more inference does not by itself produce more progress: agents replay growing histories, duplicate one another's work…A Novel Sentence Stress Detection Framework Leveraging Auxiliary Word-Stress Modeling and Loss Optimization
Prosodic stress is a crucial aspect of automatic pronunciation assessment (APA), encompassing both sentence stress detection (SSD) and word stress detection (WSD).Monte Carlo Estimation for KV Cache Eviction
Most KV-cache eviction methods ask, in effect, which memory appeared important while reading the prompt?Loud and Clear: Dynamic Activation Steering for Improving Speech Intelligibility in Noisy Environments
Speech becomes less intelligible in noisy environments, and humans naturally adapt their voice to compensate.Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security
LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial content.DLoop: Looped Speculative Decoding
Speculative decoding accelerates autoregressive generation in large language models.Improving Synthetic Data Generation for Argument Mining via Adversarial Reinforcement Learning
Argument Mining (AM) is fundamentally constrained by the scarcity of high-quality structure-annotated datasets.Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation
We study the robustness of keystroke dynamics for detecting large language model (LLM)-assisted writing.When Old Facts Return: Re-Reads, Reverts, and the Limits of Temporal Memory
A memory system can retire an obsolete value and later restore it merely because the same old statement appears again.Readout Stability in Prefill-Only Decision Models:Zero-Label Prediction and Inference-Time Compute Allocation
Prefill-only decision models inspired by the Jev model score every candidate in a menu during a single forward pass and never decode, which makes one call one to two orders of magnitude cheaper than…Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods
Activation steering provides a lightweight and flexible way to control large language model (LLM) behavior.SanSi: A Looped Typed Decision Model for System 1.5 Thinking
Typed decision models answer a declared question without generating text: a decision head returns a probability for each of the declared options in a single forward pass.Learning to Retrieve via Reinforcement Learning in Embedding Space
Dense retrieval models are typically trained with contrastive objectives that learn effective representations but do not directly optimize retrieval metrics or downstream task performance.From Evidence to Action: How Tool-Using Agents Fail
Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand.No Transformer Beats Six Covariates: Long-Horizon Prediction of Depressive Symptoms from Childhood Essays
Natural language processing (NLP) models can detect depression-related language in text written near the time symptoms are measured, but whether pretrained transformers can predict depressive…TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Reinforcement learning (RL) for post-training large language models (LLMs) incurs substantial computation and memory overhead during rollout generation, which motivates low-precision rollout for…Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models
Vision-language models (VLMs) face compositional safety risks where harmful intent emerges from the interaction between visual and textual inputs.