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 200
Correct, Don't Delete: Mitigating Emergent Misalignment with Corrective Supervision
Fine-tuning a language model on a narrow set of harmful demonstrations, such as bad medical advice, can make it broadly misaligned on unrelated questions, a phenomenon known as emergent misalignment…RLTL;DR: Self-improvement by Internalizing Self-generated Feedback
The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards the successful ones.Co-Linguistics: AI-augmented Theory Construction in Linguistics
LLMs have been studied in recent linguistics as potential models of humans' linguistic abilities.Evaluating and Benchmarking the System One Model Jev
Jev is a commercial System One model from TypeSafe AI that does not generate text: given a state and typed questions, it returns a choice from fixed options, a position on a rubric, or the…Corpus-Guided Dual-Path Propagation for Graph Retrieval-Augmented Generation
Graph-based retrieval-augmented generation supports multi-hop retrieval by organizing corpus information into graphs.KUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora
Experienced professionals know more than just facts and conclusions.When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task
One of the current premises of mechanistic interpretability research is that detailed accounts of the geometry of neural network representations can tell us how models perform computations, and how…EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?
Autonomous agents have made rapid progress in general-purpose computer use, but reliable automation of professional industrial engineering remains out of reach, as engineering workflows demand…Reader Proficiency Shapes Layer-wise Surprisal Profiles
Reading behaviour varies not only with linguistic input, but also with reader proficiency.Billiger.de Products: A Bilingual Entity Matching Benchmark
Existing product matching benchmarks primarily contain English-language product data and are often dominated by a single product category, such as electronics.Predictive Geometry of Hidden Trajectories in Transformers
Decoder-only transformers are trained only through a terminal next-token prediction loss, yet this loss constrains every intermediate hidden state through the fixed downstream computation.Context Language Models
We introduce Context Language Models (CLMs), language models that natively manage their own context.Which papyrus HTR is good enough? Character-error-rate tolerance of four papyrological tasks on Greek texts
Most Greek papyri remain unpublished and undigitised; a handwritten text recognition (HTR) pipeline that transcribes them automatically would let scholars discover documents and literary works that…Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings
Large language models (LLMs) have shown strong potential as training-free text encoders for long-context embeddings.A Proposed Rubric for Evaluating Expressed Clinical Reasoning in Large Language Model Responses
We propose a rubric for assessing expressed clinical reasoning in model responses, drawing on three bodies of work: medical education assessment frameworks (ART, SCT, Key Feature Problems and OSCE)…CompOrca: Corpus-Scale Compliance Labelling of Instruction-Tuning Data
Studying how fine-tuning shapes refusal and noncompliance behaviour requires identifying training examples that refuse, evade or otherwise fail to fulfil the requested task.Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue
Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond.The Geometry of Inference in Transformer Residual Streams
Transformer language models build predictions through successive residual updates, but how their representations become specific to an eventual outcome remains unclear.Can a Cacheable Decision Model Follow Rules?
Certo is a small non-generative decision model (Qwen3-4B): it scores candidate actions from their text and returns a probability, instead of generating an answer.Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment
Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly elicit unsafe responses.