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 158
Automatic Speech Recognition for Low-Resource Sinhala: A Critical Review of Methods, Challenges, and Future Directions
Automatic speech recognition (ASR) for low-resource languages remains a major challenge.Knowing the Rules, Applying the Rules: Evaluating Language Models on Traditional Chinese Bazi
Knowing domain rules does not guarantee applying them to a case.Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning
Reasoning models write most of their KV cache while decoding long chains of thought (CoT), so the cache has to be compressed online under a fixed memory budget.Voltic: Distinguishing Volatility from Stochasticity in Recurrent Memory
Recurrent sequence models must decide how strongly to overwrite their memory at each token.AdaSpark: Adaptive DSpark with Online Learning for Tree Verification and N-gram Fill
Block drafters such as DSpark propose ranked candidates for several positions in one forward pass, and a tree verifier checks them in one pass of the target.Mining Agent Skills from Production Traces
Agent skills that record procedural instructions are increasingly mined from execution traces rather than curated by hand.MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks
LLM agents are increasingly built for medical work and scored on clinical benchmarks.CLARA: Can AI Assess Developmental Appropriateness in Children's Stories?
Assessing the developmental suitability of children's narratives is important for educational recommendation and developmental literacy research, yet such assessment typically relies on subjective…Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
Low-Rank Adaptation (LoRA) achieves parameter-efficient fine-tuning by constraining model updates to a low-rank subspace and has been widely used in practice.Plan Canvas: Fixed Reasoning Regions for Continuous Language Flows
Continuous language flows generate text by denoising all positions of a target canvas together.Nash Equilibrium Text: A Game-Theoretic Decoding Framework for Text Generation
Text revision has become an integral component of large language models.Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training
Terminal agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored.HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
Linear attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, but this compression can make selective access to sparse and distant information…Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning
A long-standing goal of AI is a model that can continually learn and improve itself.Learning to Learn a Language
We present the Prior-Fitted Language Model (PFLM), a 300M-parameter byte-level transformer pretrained only on samples from a synthetic non-linguistic prior.Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering
Masked diffusion language models (dLLMs) generate text by iteratively denoising masked positions, re-predicting each token multiple times before it is committed.TasteRoute: Personalized Routing for Video Generation
Rapid progress in video generation has led to a plethora of models that differ substantially in capability and generation cost.HuatuoGPT-3: RL-Only Domain Adaptation from Base Models
Domain adaptation aims to turn a general-purpose large language model (LLM) into an expert for a target domain.Can Language Models Learn to Reject Their Own Bad Reasoning Steps?
Verifier-guided decoding can prevent harmful reasoning steps from contaminating subsequent generation, but typically relies on an external learned verifier.StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs
Serving a large language model (LLM) across a fleet of deployments requires several weight-precision operating points.