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 214
The Surge of Anti-Semitism in German Social Media following the October 7 Attacks
We investigate the extent to which the Hamas attacks on Israel of October 7, 2023, have affected German social media debates about Judaism and Israel.When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders
Sparse autoencoders (SAEs) expose interpretable features in large language model activations, yet existing structured SAEs impose single-parent trees or forests, while post-hoc graphs permit…MoRE: Scaling mixture of experts with hardware-aware low-rank routing
Mixture-of-Experts (MoE) layers are central to frontier language models, and recent architectures push toward more and smaller experts.HeurEvo: Agentic Evolution of Hybrid Solver-Augmented Heuristics for Time-Critical Mathematical Optimization
Recent advances in agentic heuristic design use AI agents and execution feedback to automate algorithm discovery for challenging optimization problems.Fractional State Space Transition for Long Sequence Modeling
State Space Models (SSMs) compress sequence history into a bounded recurrent state, making the resulting memory law a central architectural choice for long-context performance.Training LLMs to Verbalize Evaluation Awareness
Evaluation awareness (EA) can cause large language models (LLMs) to behave differently during audits than in deployment, yet measuring and accounting for EA remains challenging.DeepRewind: Predicting and Repairing Premature Commitments in Deep Research Agents
Deep-research agents conduct long-horizon investigations through iterative search, evidence evaluation, belief revision, and synthesis.TTMark: Pairwise Distortion-Free Watermarking Beyond Single-Token Entropy
Distortion-free watermarking enables reliable attribution of machine-generated text while preserving output distribution.Calibrated to Whom? Persona and Language Effects on Cultural Values in JEV
Decision-only language models return a probability for every answer option instead of generating text, which makes them attractive as survey respondents and as judges.Your Benchmark Is Not Saturated: Reviving Multiple-Choice Evaluation with Answer Pooling
Multiple-choice benchmarks are cheap to grade and are running out of room, and the standard remedy, writing harder items, is slow and repeated for every benchmark.Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance
We propose RegLLM, a diagnostic harness for bounded autonomy in regulated agentic workflows.Layer-Informed Fine-Tuning via Three-Stage Functional Segmentation of LLMs
In recent years, the performance of large language models (LLMs) on reasoning tasks has been remarkable, even surpassing human capabilities on various benchmarks.When Does a Spoken Agent Have Enough Evidence to Act? The PACT-SLM Contract Test
Streaming spoken agents may take an external action before the available speech supports it, yet final-turn scores do not reveal whether each observed prefix supports that action.Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs
Large language models (LLMs) are increasingly deployed in privacy-critical domains (e.g., healthcare, finance, and government), but their propensity to memorize and disclose personally identifiable…Improving the Diversity of LLM Outputs without a Trade-off
We propose DAST (Diversifying Arithmetic Sampling with TokenTour), a method that increases the diversity of LLM outputs without any change to the marginal distribution and with negligible…Pinned and Still Unstable: Within-Judge Verdict Variance and the Noise Floor of LLM-as-Judge Leaderboards
Modern LLM evaluation assumes that pinning a judge to a fixed model snapshot and decoding at temperature zero yields reproducible verdicts.Reading Too Much into Context: Passive Exposure Can Steer LLM Decisions
Large language model (LLM) assistants can now search the web and consult external sources while completing user requests.Algorithmic Harms Associated with Generative Model-Augmented Recommendation Systems
In this work, we consider algorithmic harms that may arise as generative models are incorporated into machine learning platforms.OneSign: Unifying Sign Language Understanding Tasks with One Model
SLU encompasses a diverse set of tasks, including ISLR, CSLR, and SLT.ECG-Scroll: A Long-Horizon, Streaming Benchmark and Agent Environment for Interpretation of Ambulatory Electrocardiograms
Multimodal large language models (MLLMs) can now interpret a standard ten-second, twelve-lead electrocardiogram (ECG) with clinically grounded, reward-verified reasoning.