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 243
Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance
Best-of-$N$ is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and high-quality reasoning paths.From Content Generation to Learning Support: Pedagogy-Guided Generative Video Tutors for STEM Learning
Generative AI enables scalable production of educational videos, but current systems largely focus on producing visually coherent content rather than supporting learning.You Can Tell Who's Asking: What the Web's Questions Are Made Of, and Where They Come From
Questions scraped from the web are used across academia and industry as a proxy for what people want to know.Re:CAP - Auditing Retrieval Coverage in Production RAG Pipelines
Retrieval-augmented generation (RAG) is hard to monitor in production: exhaustive relevance labels do not exist for non-stationary multi-million-passage corpora that re-index in real time.Data Agents: Agentic Data Systems
Traditional data systems face profound limitations in the AI era, relying on human-crafted pipelines, lacking semantic understanding of heterogeneous data, and operating through rigid, reactive…TAC-Time: Texts as Channels For Multimodal Time Series Forecasting
Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts.Efficient LLM Distillation for Bangladesh Legal Context: A Smartphone-Compatible Retrieval-Augmented Generation Model
Legal information in Bangladesh is inaccessible to most citizens.When Residualization Helps an Audit: Format Effects, Slice Gains, and Their Limits
Evaluation scores used around LLM systems -- including reward models, rerankers, and LLM judges -- can track surface form instead of the quality they claim to measure.LoopCD: Loop-wise Contrastive Decoding for Improving Reasoning in Looped Language Models
Looped Language Models (LoopLMs) perform "latent reasoning" by recursively refining internal latent representations with shared weights, offering a more effective alternative to explicit verbal…Vimarsha: Faithful ASR Evaluation for Indian Languages with Demographic Diversity, In-the-Wild Audio and Spelling Variations
Evaluation benchmarks for Indian language automatic speech recognition (ASR) suffer from two systematic biases: optimistic scores from clean, controlled audio conditions, and pessimistic scores from…From Articles to Publishers: Aggregating Language Model Predictions for News Source Reliability Inference
Traditionally, the reliability of news publishers is assessed by expert organisations that evaluate editorial practices, transparency and factual standards at source.Memory vs. Context? Influential Factors of Factual Recall in Language Models
We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contradictory in-context statements.Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking
Large language models (LLMs) have shown remarkable progress in natural language understanding, yet their effectiveness in specialized fields like astronomy and astrodynamics remains limited due to…Canonical Procedural Actions: An Auditable Annotation Protocol for Tool-Use Agent Traces
Tool-use agent traces identify messages and API calls, but procedural analyses also need explicit units of action and inspectable links to their evidence.Structure Before Sampling: Community-Aware Core-Set Selection for Data-Efficient Text-to-Speech
Text-to-speech (TTS) corpora are costly to record, yet many utterances add little new phonetic information.SupportCal: Label-Free Calibration of Post-Trained LLMs via Reference Support and Corroboration
Post-training often improves task performance but can degrade confidence calibration, leaving post-trained language models (PoLMs) more overconfident than their corresponding pretrained language…Morpho-VITS: Variational Inference with Morphological Modeling for End-to-End Speech Synthesis of a Tonal Bantu Language
Text-to-speech models for Bantu tonal languages are challenged by a tonal system that is rooted in both the lexis (i.e., the inventory of words, stems, and affixes) and the grammar (i.e…Mitigating Entity Type Confusion in Cross-Domain NER via Multidimensional Quantification and Reasoning Enhancement
Cross-domain Named Entity Recognition (CD-NER) aims to transfer the rich knowledge in the source domain to the target domain.URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER
In-context learning (ICL) based on large language models (LLMs) has shown promising potential in alleviating performance bottlenecks caused by the limited availability of annotated data in Named…End-to-end Jordanian dialect speech-to-text self-supervised learning framework
Speech-to-text engines are extremely needed nowadays for different applications, representing an essential enabler in human-robot interaction.