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 160
DP-ES: Differentially Private Evolution Strategies for Prompt Optimization
Token-level differentially private (DP) prompt optimization methods such as DP-OPT can become unstable under tight privacy budgets: on GSM8K, DP-OPT obtains $49.5\pm28.5\%$ across 30 runs, and a…Shared Stopping Decisions Change Answers in HQQ Cache Quantization
Language-model systems batch questions for throughput, but unrelated questions should not change a target's answer when its input and numerical execution are fixed.Probabilistic Race and Ethnicity Prediction Using Group-Specific Name Lists
Statistically valid estimation of racial and ethnic disparities often requires inferring the probability that an individual belongs to a particular racial or ethnic group given only their name and…DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression
Long-context large language models (LLMs) have demonstrated strong capabilities across a wide range of tasks, but the growing KV cache introduces substantial memory and inference overhead.From Abusive Language Classification to Sequence Labeling Identification
Industrial content moderation must process massive message streams under tight latency constraints, yet most abusive language (AL) detection systems rely on sentence-level classification (ALC)…DialectSentEval 2026: Arabic Dialect Sentiment Analysis and Swapping Shared Task
Sentiment analysis is a fundamental problem in Natural Language Processing (NLP).Agentic schema-guided extraction of materials process knowledge from scientific literature
Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported in heterogeneous forms and…Breaking Bureaucracy: Evaluating open-source LLMs for legal document review
In this paper, we evaluate open-source generative LLMs on legal Natural Language Inference (NLI).Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering
Reinforcement learning post-training for language models relies on two reward designs: human preferences (RLHF, DPO) and binary verifiers (RLVR).Steering by Influence: Curvature Aware Data Weighting for Activation Steering
Inference-time steering offers cheap, fine-grained control over a language model's outputs by estimating a concept's representation in activation space and shifting activations towards it.RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content.What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents
As agents take on long-horizon tasks, users shift from making individual decisions to overseeing autonomous execution.SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs
Thinking-enabled vision-language models (VLMs) report ever-higher accuracy on spatial benchmarks, yet final-answer scores cannot reveal whether a correct prediction reflects faithful spatial…Do Speech Representations Preserve Regional Accent Across Read and Spontaneous Speech?
Regional accent cues can be captured under matched conditions, but it remains unclear whether they persist between read and spontaneous speech.HeuFouFT: Task-Guided Metaheuristic Coordinate Search for Fourier Fine-Tuning
We introduce Heuristic-Guided Fourier Fine-Tuning (HeuFouFT), a task-guided framework for selecting trainable frequency coordinates in Fourier fine-tuning.Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models
What happens when a legal AI model learns to look like a lawyer instead of reasoning like one?The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning
Large language models (LLMs) trained to answer questions are natively poor at teaching.Behavior-Preserving KV Cache Compression
KV caches are a major bottleneck in long-context inference and long-form generation with large language models.AECP: Artifact-Exclusive Communication Protocol for Multi-Agent Code Generation
As AI agents increasingly tackle complex repository-level coding tasks, distributing work across multiple agents is a natural way to scale beyond the capabilities of a single agent.SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics
Evaluating text generation requires measuring how well the generated distribution matches the data distribution.