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 194
Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities
Large Language Models increasingly serve as interfaces for knowledge-intensive information seeking tasks across languages by synthesizing multilingual evidence.Legal Research Bench: Measuring End-to-End Reliability in Long-Horizon Legal Research Agents
Legal research is a core and time-consuming legal workflow.Explainable Suicide Risk Assessment on Social Media with Multi-Task QLoRA
Explainable suicide-risk assessment requires models not only to estimate risk severity, but also to identify supporting language and the risk and protective factors expressed in a post.Mixture of Decoders for Diverse Dialog Response Generation
Mixture modeling is a long established machine learning technique for learning large sets of multi-modal data.Self-Evolving Coding Rules for AI Coding Agents
The performance of AI coding agents is highly dependent on their underlying coding rules.Lingtai: What Concept Geometry Reveals--and Does Not Reveal--About LLM Inference
Observing what a large language model computes during autoregressive inference--online and without training probes--remains difficult.PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation
Bengali secondary education lacks curriculum-grounded benchmarks for STEM question-solving, and general-purpose language models struggle with the precise terminology, unit conventions, and…Closing the Loop: Practical Training Recipes for Looped Language Models
Looped language models increase effective depth by repeatedly applying a shared block of layers, but existing large-scale recipes require multi-stage training over trillions of tokens, while the…Bayesian Fine-tuning Yields Language Models that are as Bayesian as their Beliefs Allow
Language models (LMs) are increasingly used for tasks that require reasoning about hidden variables from a few observations, for which Bayesian inference is the normatively correct solution.Towards Robust Numerical Claim Verification
Large language models (LLMs) are widely used for claim verification, yet remain brittle for numerical reasoning: even small changes in value can sharply degrade accuracy.How Divergence Becomes Decision Flips in Compressed Language Models
Compression reports summarize how far a compressed language model moved from the dense one, usually by a KL divergence; a deployment that relies on the dense model's outputs needs to know how many…Initialization Improves LLM-Driven Discovery
Large Language Models (LLMs) have been used for novel discovery of algorithms, theorems, drugs, and other tasks through the use of harnesses that prompt an LLM to iteratively optimize an objective.Sequential Functional Structured Tucker Compression for Large Language Model Attentions
Post-training compression of LLM attention is often formulated as independent matrix approximation, ignoring both the shared structure among attention projections and the representation shift…Reason in Style: Discovering and Controlling Style in Language Models
Language models learn content and style jointly, making stylistic variation in their outputs difficult to identify and control.Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints
Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later training.Effective Synthetic Data Curation Requires Group-Level Signals
Synthetic data now is essential to LLM training, used to strengthen advanced capabilities such as autonomous and long-horizon task execution.Can large language models unlock discrete data in ophthalmic diagnostic reports?
To assess the accuracy and efficiency of a large language model (LLM) using two prompt strategies to extract structured data from ophthalmic diagnostic PDF reports.Sapien: A Stateful Policy Engine for Autonomous AI Agents
Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls.Paying for Too Many Tokens? Valid and Cost-Efficient Multimodal LLM Annotation with Simple Heuristics
Vision-Language Models (VLMs) enable video annotation at scale, but costs accumulate quickly: processing a typical 60-second short-form video at one frame per second requires millions of tokens.TabJoinBench: A Benchmark for Joinable Table Discovery
Join discovery aims to identify tables from large data repositories that can augment a query table with complementary information, enabling downstream tasks such as data exploration, feature…