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 18 September 2026 to 6 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 215
MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning
Medical question answering spans diverse specialties and modalities, and individual medical large language models (LLMs) exhibit distinct strengths across tasks and domains.Classifying Dominant Temporal Orientation without Pretrained Text Embeddings: A Novel Morphosyntactic Inventory Vector Approach
Computational methods have consistently struggled to determine the dominant temporal orientation of a sentence.Save Your Saturated Data: Learning Beyond Reward Saturation in Group-Based RL
Group-relative reinforcement learning (RL) relies on reward variation among sampled responses to estimate informative relative advantages.Knowing Is Not Choosing: What Explicit Verification Adds Beyond Generative Preference
Generating a correct answer does not mean that a language model will select it.CAME: Company-Aware Evidence-Memory Experts for Interpretable Quarter-Ahead Revenue Forecasting
Quarter-ahead revenue forecasting requires company-scale numerical accuracy, strict temporal validity, and company-specific interpretation of narrative disclosures.Generalization Dynamics of LM Pre-training
People typically assume that LMs stably mature from pattern-matching parrots to generalizable intelligence during pre-training.Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction?
Test-time scaling and post-training have improved LLM performance in coding and mathematical reasoning, but their effectiveness for individual stance prediction remains unclear.Scoring the Wrong Question: Readout Failures in Constrained-Option Evaluation
Constrained-option scoring reads a model's probabilities for a fixed set of permitted answers, so it returns a score even when the model is about to write something else.SeOPD: Self-Evolving LLMs via Online Policy Distillation from Self-Generated Chain-of-Thought
Recent advances in online policy self-distillation (OPSD) have demonstrated that large language models (LLMs) can improve their capabilities by leveraging external privileged information (PI), such…Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall
Large Language Models (LLMs) suffer from temporal misalignment, often due to the contradictory nature of their training corpora.AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits
Scientific code generation can produce executable programs that fail to compute the intended scientific object.Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning
On-policy self-distillation trains reasoning models on their own trajectories using dense token distribution guidance from a privileged teacher with access to a verified solution.Turning Speech Language Models into Multilingual Listeners
Speech Language Models (SLMs) that understand spoken language questions support only a few high-resource languages, limiting access to millions of people worldwide.Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms?
Typed-decision models such as TypeSafe's Jev answer a declared yes/no or multiple-choice question about a state with a probability instead of text, and their evaluations report accuracy and…CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification
Speaker verification systems achieve high accuracy but provide little account of the acoustic evidence behind their judgments.When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning
Outcome-based reinforcement learning can produce models with similar task performance but very different ways of communicating about their mistakes.Beyond Memory Construction: Rethinking Memory Access for LLM-based Conversational Agents
Memory is a core component of conversational agents, enabling coherent and context-aware behavior over long interactions.Acoustic Progress Propagation for Long-Horizon Speculative Decoding in ASR
Speculative decoding accelerates autoregressive automatic speech recognition (ASR), but the acceptance length of alignment-aware drafters can saturate as the draft horizon increases.BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions
Understanding how drugs interact with protein targets is fundamental to drug discovery, drug repurposing and the early identification of promising therapeutic candidates before costly experimental…The Text Beside the Image: Detection, Utility and Leakage for Trustworthy Multimodal Medical Data and Beyond
Medical images are released with the reports that describe them, and protecting the image does not protect the report.