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 96
Encoder-Free Multimodal LLMs Learn Implicit Encoders
We empirically analyze two recently proposed encoder-free multimodal LLMs, Gemma-4 12B and Inkling-Small.Probing Ambiguity: Adversarial Intent Resolution for Robust Text-to-SQL
Text-to-SQL systems typically assume a one-to-one mapping between natural-language queries and correct SQL translations.Can This LLM Annotate My Data? Estimating Zero-Shot LLM Performance
Large language models (LLMs) are increasingly used in annotation tasks with varying success.SLA-LENS: From Classroom Transcripts to CSLA-Informed and Evidence-Linked L2 Interaction Analytics
What happens after a learner makes an error, and how does the instructor's response shape the next turn?Best of Both Worlds: Fine-Tuned Small Models Complement LLMs for Cost and Performance Benefits
BERT-based models require thousands of labeled samples to train.Desirability Confirmation: Relational Sycophancy in AI Intimate Roleplay
Research on LLM sycophancy has largely focused on propositional agreement, in which models echo users' beliefs, preferences, or judgments.Modeling bilingual naming performance through laterally-connected SOMs
Computational models have explanatory power to understand cognition in individuals, but there is usually not enough training data to build such models with traditional machine learning.BanglaShield: A Script-Robust Safety Classifier and Benchmark for Bangla Native, Romanized, and Code-Mixed Prompts
Safety classifiers for large language models (LLMs) are typically built and evaluated on standard-script text, yet Bangla, like many lower-resource languages, is routinely written in native script…Beyond Clean Accuracy: The Practical Challenges and Benefits of Pixel-Based Language Models
Pixel-based language models process rendered text without relying on a fixed subword vocabulary, offering a promising approach to noisy and multilingual inputs.Not Every User Says It All: Training Tool-Using Agents Beyond Ideal Simulated Users
Tool-using agents are trained and evaluated almost exclusively with strong simulated users who state every detail clearly, yet real users are often weaker.The Judge Can Debias Itself: Awareness and Self-Debiasing for Reliable LLM-as-a-Judge
LLM-as-a-Judge systems are increasingly employed for automated evaluation, yet remain susceptible to systematic biases that undermine their reliability.Learning When to Think: Utility-Guided Adaptive Reasoning for Efficient Text Retrieval
Reasoning-conditioned embeddings can improve retrieval by progressively refining semantic constraints.INCONVENIENT: A Benchmark to Assess LLM Generalization Capabilities from Convenience Samples
Machine learning models for tabular prediction typically assume that training data are representative of the population on which they will be deployed.ReviewPilot: A Multi-Agent System for Screening and Data Extraction in Systematic Reviews
Systematic literature reviews follow the PRISMA process of screening scholarly works and extracting evidence from included studies.PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews
Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate what a paper says.SHIP: Structured and Hierarchical Insight with Privacy
Extracting insights from textual data while protecting user privacy is increasingly important.Athanor: An Agent-Native System for Autonomous Post-Training Research
Recursive self-improvement, in which AI systems build stronger AI systems, is one promising route to superintelligence.Multimodal AI Detection for Math-Heavy Scientific Text
As large language models become increasingly capable of generating, and assisting with, scientific writing, there is a need for greater transparency and disclosure around the use of AI in research.A Jury, Not an Electorate: Label-Free Reliability Estimation for Ensembles of Language Models
An ensemble of language models is a jury, not an electorate.MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning
Agent memory enables large language model (LLM) agents to reuse past experiences without updating their parameters.