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 74
A Reverse-Gold Theorem: Positive-Data Identification by Substrate-Bounded Contrastive Learners
Gold's theorem shows that no learner can identify an arbitrary language in a superfinite class from positive presentations alone.Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model often requires domain…SkillEval: Learning Interpretable Ability Profiles of LLMs via Cognitive Diagnosis Models
Current evaluation of LLMs on benchmarks typically aggregates performance over individual examples into a single scalar score.Scaling Therapy Supervision: Assessing Psychotherapy Fidelity Using Large Language Models
Psychotherapy fidelity assessment measures how faithfully a therapist adheres to a treatment protocol, a critical determinant of positive patient outcomes.Measure First, Then Allocate: Calibrated Rollout Budgets for MCP Agents in Reinforcement Learning
Training tool-using language models requires costly interaction, yet identical rewards within a rollout group provide no group-relative learning signal.Is Anyone Enforcing the Cartel? What Reinforcement Learning Teaches LLM Agents in Markets
Evaluations of large language model (LLM) agents report that pricing agents collude at others' expense.CALLIOPE: Private Insights into AI Use, Without Embeddings
We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g., LLM conversations), while supporting differential privacy (DP).Where Do Legal Factors Live in LLMs?
In case-based legal reasoning, legal professionals identify legally significant fact patterns in a new dispute and compare them with those of decided cases.Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks.LIFT: Scoped Constraints for Evaluating and Training Instruction Following
Common instruction following (IF) benchmarks, such as IFEval, evaluate the ability of language models (LMs) to follow simple constraints that can easily be verified programmatically.A Parallel Multi-Dialect Arabic Dependency Treebank
Dependency parsing resource development for Arabic has largely focused on Modern Standard Arabic, leaving dialectal Arabic comparatively under-resourced.Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources
Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback.How to Use Parallel Data for Multilingual Pretraining
High-quality human-translated parallel corpora can improve cross-lingual transfer, but are typically too small for large-scale pretraining.KIRA: A Full-Stack Reading Screening System with Dual-Pathway Analysis for Children
Early-grade reading screening is critical for identifying children at risk of reading difficulty.Beyond Correct Answers: How Compositional Cues Shape Visual Judgments
Visual question answering requires models to assign attributes and relations to the correct objects, a problem known as visual binding.To Manipulate or Not: Opinion Dynamics in LLM Interactions
Large language models increasingly take part in extended conversations where they can both shape and be shaped by another party's views, yet most persuasion research measures only one side of that…SANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges
LLM judges increasingly mediate benchmark evaluation, model selection, data curation, and training.Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures
Autonomous agents can increasingly propose ideas, modify code, and run experiments, creating an opportunity to accelerate scientific discovery using teams of collaborative AI researchers.CSD: Common-Support Distillation for Cross-Tokenizer Knowledge Transfer
Cross-tokenizer logits distillation enables knowledge transfer across model families, allowing students to learn from stronger or more specialized teachers.Is Refusal Direction Universal across Low-Resourced Languages?
Refusal directions have been shown to transfer cross-lingually with near-perfect effectiveness across safety-aligned languages (Wang et al., 2025), reportedly regardless of resource level.