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 142
Smoothing the Top-k Exposure Boundary for Sparse Mixture-of-Experts
Sparse Mixture-of-Experts models scale parameter capacity efficiently while maintaining a fixed compute budget per token.Chronos Enables Code Agents to Reason over Software Evolution
Historical pull requests record the design decisions, compatibility constraints, and implementation patterns behind a codebase's current state.Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection
Recent advances in large language model (LLM) pretraining highlight the role of high-quality training data in improving performance.Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health LLM Interactions in Indian Contexts
Existing evaluation methods for healthcare LLMs primarily assess factual correctness,safety, and fluency, while providing limited insight into whether generated interactions reflect culturally…Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog
Current frontier LLMs can theoretically process long contexts with 1M tokens or more.Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing
Journals and conferences have begun to screen submitted manuscripts for text written using large language models (LLMs).UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactions
Evaluating user experience (UX) with automated computational methods has gained increasing attention, supported by empirical evidence from UXBench.Phonologically Informed Tokenization for German Speech Recognition: A Cross-Domain Study
German is a morphologically rich language whose syllable structure is exceptionally well-predicted by the Knuth--Liang hyphenation algorithm.Harness Evolution Hits a Ceiling: When Weight Training Should Begin
Improving a long-horizon LLM agent means evolving the harness around a frozen model or training its weights.DIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation
On-policy distillation (OPD) supervises student-generated trajectories with token-level teacher signals.TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation
Verifier scores now serve as both benchmark metrics and training rewards for large language model (LLM) agents, and a change in score is routinely read as a change in capability.Structured Sentiment Analysis Using Sequence Labeling as Dependency Graph Parsing
This study addresses the problem of structured sentiment analysis, whose goal is to obtain a fine-grained sentiment graph where the nodes represent spans of sentiment holders, targets, and…Internalizer: Portable Context-to-Parameter Mapping for Very Large Language Models
Hypernetworks that map a context directly to a LoRA adapter let a large language model carry that context in its weights, but prior work has demonstrated them only on base models of up to 14 billion…4-Tensor Attention Model for Semantic Physical Reality
We describe a 4-tensor attention model that predicts the next semantic state of a scene, for video generation and robot planning.Thinking Inertia: LLMs Keep Thinking When Told Not To
Large Language Models (LLMs) increasingly ship with explicit "thinking modes", yet their counterpart, "no-thinking", has received far less attention.Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation
Safety evaluations of large language models commonly summarize harmful-output behavior with attack success rate (ASR).RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
Sparse Mixture of Experts (MoE) models scale more efficiently than dense models by routing tokens to modular expert networks that are only active for processing a fraction of tokens.DPPM: Dual-Path Parametric Memory for Personalized Language Models
Long-term personalization requires language models to use interaction history to track users' preferences across sessions.From Sparse Representations to Behavioral Insights for Multimodal Depression Assessment
Multimodal depression assessment offers a promising approach to analyzing behavioral patterns associated with depression.Easy to anticipate, hard to compute: boundary dependence finds the computed outputs that entropy patching misses
Byte-level language models such as the Byte Latent Transformer (BLT) group bytes into patches and run their large global model once per patch.