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 23
ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens
Despite advances in retrieval-augmented generation (RAG), suppressing hallucinations during complex reasoning remains a persistent challenge.What Breaks and What Comes Back: Capability Damage and Recovery in Depth-Pruned Small Language Models
Depth pruning removes whole Transformer blocks to make a language model smaller and faster, but the damage is not spread evenly across what the model can do, and a short fine-tuning run, called…Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand
Benchmark compression reduces the often prohibitive time and cost of model evaluation by evaluating models on a small benchmark subset that closely matches full-benchmark results.When 200 OK Is Not an Answer: Silent Fetch Failures in Agentic Web Content Acquisition
Web agents and answer engines fetch pages at question time, and liveness checks of cited sources treat an HTTP 200 response as success.S1CogBench: What System One Decision Models Can and Cannot Do on Cognitive Experiments
Language models are no longer used only to generate text.Labadain-MedQA: A Tetun Medical QA Dataset for Fine-Tuning and Evaluating Large Language Models
Advances in large language models (LLMs) have created opportunities for cross-lingual transfer of medical knowledge from high-resource to low-resource languages to support access to healthcare…Reformulation and Equivalence of Bock's Algorithm for Exact Dependency Parsing
Bock's algorithm provides a matrix-based alternative to Chu--Liu/Edmonds (CL/E) for exact dependency parsing.Self-Refining Prompt Induction for Streaming Text-to-SQL
Text-to-SQL assistants for streaming engines must handle dialect-specific types, windowing rules, and temporal semantics, including constructs poorly handled by generic prompts.A Token Is Not a Unit of Difficulty: Segmentation Controls Where Adaptive Computation Goes Inside a Word
Early-exit language models decide for each token how much computation to spend, usually by stopping once the prediction is confident.HALO: Hierarchical Evidence Selection and Reinforcement Learning for Allocating Budgeted Label Optimization from Longitudinal Clinical Records
Learning from extensive longitudinal clinical records--spanning repeated encounters, evolving conditions, and heterogeneous documentation--under a finite labeling budget requires solving two coupled…Label Smoothing in Disguise? Gated Knowledge Distillation for Low-Resource Bangla Generation
Gated knowledge distillation (KD) weights teacher signals per token or example, aiming to trust an imperfect teacher only where it seems reliable.Multi-Turn Semantic Caching for Low-Cost LLM Serving
Semantic caching lowers the cost of serving large language models (LLMs) by reusing stored responses for similar requests.CogRSI: Evolving and Auditing Cognitive Reasoning Strategies
Can a language model learn better ways to reason about other people's minds by improving its own strategies, and are the strategies it learns actually right?CompSkill: Compiling Execution Experience for Skill Retrieval
LLM agents increasingly rely on skill documents, yet most retrievers rank them by description alone and ignore what earlier executions revealed, even though a relevant skill can hurt execution.Zero-Gated Cross-Attention
Injecting non-text modalities into frozen language models often introduces early optimization instability, making it difficult to separate architectural gains from transient training dynamics.Do Earnings Calls Help Predict Financial Restatements? Evaluating Text Beyond Public Firm Information
Financial restatements correct errors in previously published financial reports.Rethinking LLM Pruning via Test-Time Scaling
Structured pruning reduces the size of large language models, often at the cost of lower accuracy.GSLM2: Multi-Stream Speech Representation Learning and Generative Spoken Language Modeling
Generative spoken language models (SLMs) offer a route to learning linguistic structure purely from speech, yet they lag far behind text-based models in both capability and data scaling efficiency.Concept-Guided Prompting Strategies Increase Diversity in LLM-Generated Recipe Populations
Novelty in solution generation supports automated discovery, but LLM outputs can remain repetitive.TRIAGE: Reliability- and Load-Conditioned Escalation for Two-Tier LLM Serving with a Semantic Evidence Judge
Two-tier LLM serving escalates selected requests from a small model to a large one, but prompt-based routers cannot see whether retrieved evidence supports an answer, and they treat the GPU cost of…