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 170
What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects
Harness search keeps a change to the prompts, reasoning switches, token budgets or parsers around a frozen model if the change raises a score.Dataset Signatures in Human-LLM Interactions and User Modeling
Human--LLM interaction datasets shape our understanding of AI use and provide a foundation for downstream research, including training and evaluation of user models.SALUS: Automated Auditing of NL-to-SQL Benchmarks through Weak Supervision of Multi-Agent Output
Natural language to SQL (NL-to-SQL) benchmarks are foundational to progress in data analysis research, yet recent work has shown that widely-used benchmarks contain significant annotation errors.Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential
Mechanistic interpretability has emerged as the primary means to understand safety behavior of LLMs.Lend Me Your Eyes: Instruction-Aware Text Embeddings via Attention Relay
Text embedding models trained with contrastive learning learn to follow task instructions from instruction-paired data, while instruction-tuned LLMs already know how to follow them.Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters
Much of expressive text-to-speech research rests on an untested assumption that written text carries enough information to select an appropriate prosodic style for its delivery.Expanding LLM Reasoning
Extra inference compute is usually spent on sampling more reasoning chains.ColdDDI: Evaluating Knowledge Utilization in Cold-Start Drug-Drug Interaction Prediction
Cold-start drug-drug interaction (DDI) prediction tests whether models can identify clinically significant interactions for drugs without training-time interaction history.What Is a Repeated Token Worth? The Scaling Geometry of Multi-Epoch Pretraining
As pretraining increasingly repeats data, every run faces three questions: how many epochs to take, how that number should change with model size, and whether anything besides the epoch count matters.More Than Words: Compositional Tokenization for Efficient Language Models
Language models process and generate text sequentially in token units, and the tokenizer determines how much text each inference step covers.DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate
Multi-agent debate (MAD) has emerged as an effective paradigm to improve the reasoning capabilities of large language models (LLMs) and is increasingly being extended to multimodal settings.Atomic Visual Entailment: Enhancing Zero-Shot Vision-Language Reasoning through Atomic Fact Decomposition and Learned Selection
Visual entailment (VE) asks whether an image supports, contradicts, or leaves undecided a textual hypothesis.Mask-Guided KV Cache Eviction in Block Diffusion Language Models
Block diffusion language models keep a large key-value (KV) cache throughout generation and attend to it at every denoising step, limiting both memory capacity and generation speed.Calibrated Answers About Randomized Trials From a 4-Billion-Parameter Open Model: A Registered Test and a License-Clean Release
Fiorillo v0.5 is an open model that answers typed questions with a probability for each answer.Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment
Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to jailbreak attacks that elicit harmful or unsafe outputs.Investigating Model Compression for Neural Machine Translation in the Biomedical Domain
Large-scale pretrained transformer models have achieved state-of-the-art performance across diverse machine translation tasks, including multilingual settings.Principled Top-$k$ Selection for Language Models with Hybrid Gradients
Selecting the best $k$ items out of $m$ candidates is a critical component of modern large language model systems, such as document selection in Retrieval-Augmented Generation (RAG) and expert…DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controls
Large language model writing interfaces often make users steer outputs by repeatedly articulating desired changes in natural language.Language Model Activations Inhabit Privileged Error-Correcting Basins
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering.Clean: Second-order LLM Training at Linear Memory Cost via Nyström Sketching
Training large language models (LLMs) entails a fundamental trade-off: memory-efficient optimizers such as Adam discard cross-parameter curvature, whereas full-curvature methods such as SOAP can…