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 132
The Constitution Speaks Nheengatu: An Open MT System and Reproducible Corpus Pipeline for the Amazonian Língua Geral
Nheengatu (yrl), the Amazonian Língua Geral, has 6--10 thousand speakers and is co-official in São Gabriel da Cachoeira (Brazil), yet remains poorly served by evaluated Portuguese--Nheengatu MT…CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation
Multimodal large language models (MLLMs) can reproduce sensitive, copyrighted, or unsafe information from their training data.Who Receives Respect? A Counterfactual Benchmark for Honorific Allocation Bias in Bengali
Bengali has no grammatical gender, but honorificity is obligatory: every third-person reference must choose ordinary or respectful register.Training-Free BioNEL-RAG: Advancing Biomedical Entity Linking through Retrieval-Augmented Generation and Large Language Model
Biomedical Named Entity Linking (BioNEL) is the task of mapping mentions extracted from biomedical texts to canonical entities or concepts in the standardized knowledge base.Dependency Reasoning for Aspect Sentiment Quadruple Prediction
Aspect Sentiment Quadruple Prediction (ASQP) is fundamentally a relational reasoning problem: identifying aspect-opinion-category-sentiment quadruples requires modeling structured dependencies, not…Social Bias in Chinese Large Language Models under Social Media Expressions
Existing Chinese social-bias benchmarks for large language models largely rely on normalized or template-based expressions, leaving the influence of internet slang, emoji, and sarcasm insufficiently…Agent-Guided Evidence Acquisition for Emotion-Cause Pair Extraction
Emotion-Cause Pair Extraction (ECPE) requires identifying the causes associated with emotions expressed in a conversation.Description Complexity Bounds for Analytic Approximations of Lipschitz Functions
We study how many bits are needed to write down an elementary analytic expression that uniformly approximates a Lipschitz function.TeachGrade: Training-Free Short Answer Scoring with Teacher Evidence
Multi-subject, multi-step scoring requires consistent partial credit across grading conventions.WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions
Developing terminal-based agents for long-horizon execution demands synthetic tasks that tightly couple complex instructions with authentic, interactive environments.SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications
Evaluating an agent's ability to strictly satisfy diverse and procedurally complex requirements is essential to determining its practical reliability.FidelityQ: Preserving Predictive Fidelity in Ultra-Low-Bit Language Model Quantization
Ultra-low-bit scalar quantization offers a regular arithmetic structure for efficient deployment of large language models, but preserving predictive behavior at extreme precision remains…Predicting how model propensities generalize out of distribution
How do language models generalize from their training data?Do Personalized LLMs Need the Whole Conversation? Matching the Full History with Only 5% of Its Text via Relevance-Filtered Context
Personalized assistants accumulate long conversation histories, and passing the whole history to an LLM with every request is costly.What Survives When Activation Steering Is Used as Memory
Activation steering has recently been used as a memory for skills: past experiences of an agent are stored as steering vectors and retrieved later.AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery
Formulaic alpha mining seeks to discover executable expressions that capture predictive market signals in a vast, noisy search space.HiPAD: A Unified Gait, Audio-Visual, and Personality Fusion Network for Depression Detection, with a Hierarchical Personality Ablation and the Calibration Limits of Domain-Adapted LLMs
We present HiPAD, a single fusion network submitted to all six sub-tracks of the MPDD-AVG 2026 depression-detection challenge, covering the Elder and Young cohorts and three modality sets (gait…HodgePhaseNet: Discrete Hodge Decomposition of Semantic Flows in Transformer Attention
WavePhaseNet introduced frequency-resolved semantic representations, QuantumPhaseNet introduced gauge-covariant phase connections, and ModularPhaseNet made a finite cyclic phase channel and its…UltraBERT: Beyond the Limit of BERT Pre-Training
Recent bidirectional encoders have been modernized with innovations from causal large language models (LLMs).Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explainability of Decision Foundation Models
Automated disease classification from patient-reported symptoms requires balancing the speed of lightweight discriminative models against the contextual understanding and latency costs of…