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 90
GRaSP: Latency-Aware Optimization for Geo-Distributed Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) is increasingly served across geo-distributed cloud and edge infrastructures, where wide-area latency, cross-region egress cost, and data-residency rules compete…Self-Evolving Coding Agents via Harness-Policy Optimization
Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the harness that mediates their interaction with…Prune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning
Fine-tuning large language models (LLMs) on proprietary records enables domain adaptation but introduces two challenges: (i) privacy leakage of memorized private data, such as personally…Causal Latent Workspaces for Looped Transformers
Reusing a Transformer block across depth increases computation without replicating its parameters, but successive passes have no dedicated state through which positions can exchange compact…Reasoning Reranking with Semantic IDs as the Sole Item Representation
Reasoning rerankers write a rationale before ranking a candidate slate, and existing systems read item metadata to do so, even though generative recommenders increasingly represent items as compact…Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction
Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts containing personally identifiable information (PII) to remote providers exposes…On the Position Bias of Large Language Models: A Comprehensive Study
Recent studies have shown that position bias remains a critical vulnerability in large language models (LLMs), undermining both the integrity of multiple-choice evaluations and the reliability of…Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks
Language-model watermarks can help identify model-generated text, encode provenance information, and detect post-generation edits.Causal Edit Serialization
Standard autoregressive language models generate text sequentially, but revision requires referring back to tokens in the input context or those already generated.Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors
Expressive speech synthesis can now change emotion within a single utterance, yet its impact on deepfake detection remains unclear.The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level Falls
Chain-of-Thought (CoT) faithfulness matters for monitoring, explaining and safely deploying large language models, yet it has been studied mostly in English.Uncertainty-Aware Budget Allocation for Efficient LLM Tree Search
Tree search enhances multi-step reasoning in large language models (LLMs), yet prevailing methods expand every step with a fixed budget, irrespective of the marginal utility of expansion.Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data
LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate directives with adversarial prompt injections, and the model must follow the…Cooperation Without Adaptation: LLM Agents in a Collective-Risk Dilemma
Language-model agents are increasingly deployed to act on behalf of people in settings where individual decisions shape shared outcomes.Batched Contextual Reinforcement II: Does RLVR Need Long Rollout Windows?
Long rollout windows make reinforcement learning with verifiable rewards (RLVR) expensive, yet simply shortening them can remove the correctness signal: when every single-problem rollout truncates…NLData2Opt: Benchmarking Parameter Derivation and Prediction for Modeling Optimization Problems from Natural Language and Data
Formulating optimization problems from raw inputs of problem descriptions and data is time-consuming and costly.Bengali Hallucination Detection with Retrieval and Programs: A System Study
Bengali hallucination detection must distinguish unsupported factual claims from incorrect reasoning, often without a supplied reference passage.Competence-Based Evaluation of Logical Reasoning in Large Language Models
Recent advances in large language models (LLMs) have brought impressive performance across diverse tasks; however, shortcomings remain in logical reasoning, including inconsistencies under…FederatedBytes: Tokenizer-Free, Byte-Level Small Language Models for Efficient Multimodal Federated Learning
Federated Learning (FL) is a powerful machine learning framework that allows building a global model from the contributions of multiple, distributed clients, while ensuring the privacy of their…Where's the Indirect Evidence? Investigating Grammatical Generalization with Influence Functions
Language models generalize beyond their training corpus to learn linguistic phenomena (Patil et al., 2024; Misra and Mahowald, 2024), showing that there exists indirect evidence driving learning.