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 118
Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key
Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be traced to its origin.PRISM: Calibrating Black-Box Judges with Counterfactual Probes
Large language models are increasingly used as judges to reduce reliance on costly human evaluation, yet their scores can systematically disagree with human judgments.Multi-Stream Residual Computation in Diffusion Language Models
Diffusion language models reconstruct masked tokens in parallel, offering an alternative to autoregressive generation.Prompt-Injection Probes Learn the Conversation, Not Just the Injection
Linear probes on a model's hidden states are used as cheap monitors for indirect prompt injection: they screen the tool outputs an agent reads and send suspicious ones to a slower second check, so…Not All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs
Prompt-based adaptation offers several ways to specialize a frozen language model, ranging from natural-language prompt optimization to learned continuous prompts.Revisiting the Estimation of Unigram Surprisal in Computational Psycholinguistics
Contextual and unigram surprisal are standard predictors of reading time in computational psycholinguistics.Do Factuality Methods Make LLMs More Factual? Reproducibility and Fair Comparison
Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps.Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages
We trained Agaram 2.5B, a 2.5-billion-parameter Tamil-English language model, from scratch on about 50 billion tokens (58% Tamil, the rest English, math, code and parallel text) on one node of eight…Receiver Decides Agent-to-Agent Negotiations
When one language-model agent asks another for money, which of the two decides how much changes hands?Reliable Memory from Unstable Growth: Curating Self-Written Agent Playbooks with Randomized Experiments
Persistent textual memory lets language-model agents reuse lessons from past tasks to improve on future multi-step tasks without retraining.Estimating Surprisal from the Speech Signal
Although language is predominantly spoken, empirical tests of surprisal theory rely almost entirely on written text.Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit
In search engines and assistants, long-form RAG answers can mislead readers with claims their sources do not support.Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints
External tools can extend the capabilities of small language models (SLMs), enabling their deployment in resource constrained environments.Readout Scaling Shapes Sparse Feature Recovery
Readout scaling changes what a sparse autoencoder (SAE) learns, but the benefit of removing it depends on the data.How Safe Is ChatGPT Health Advice? Evidence from Real User Conversations in Four Global South Countries
People increasingly bring their health questions to ChatGPT, yet safety evaluations of LLM health advice rest almost entirely on clinician-authored vignettes, synthetic prompts, or simulated user…Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments
Tool-call judges evaluate argument values proposed by LLM agents.Aligning Faithfulness for Theory-Scale Autoformalization
Autoformalization (AF) requires more than compilation: formal statements must preserve the meaning of their informal sources, a property known as faithfulness.The Last Mile of Coding Agents for Long-Document Tasks: An Empirical Study on Clinical Trial Protocol Digitization
Clinical trial protocols serve as the source of truth for study design, but are mostly written and used as unstructured PDF documents.Imprinting: Knowledge Distillation Can Shift Student Behavior
Knowledge distillation trains student models on teacher-generated responses to transfer task capability, but those responses may also carry behavioral tendencies of their source.The Geometry of Language Model Logits: Generic Structure and Learned Departures
Autoregressive language models produce, at every prediction step, a vocabulary-sized logit vector whose structure determines the conditional next-token distribution.