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 129
The Fragility and Dynamics of LLM Pruning-Recovery Steps
Structural pruning followed by a recovery stage is the standard recipe for compressing large language models (LLMs), yet the two stages are typically designed and tuned in isolation.Towards Robust Calibration Dataset for Domain-General Mixture of Experts Pruning
Post-training expert pruning is a promising deployment technique for Mixture-of-Experts (MoE) models.The Gradient That Top-k Distillation Never Computes
Many deployed distillation pipelines show the student a truncated view of the teacher: keep the top-k probabilities, renormalize, and minimize a divergence on what remains.Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement
Feedback presentation shapes how LLMs use evaluator judgments during translation refinement.A Persian Vision-Language-Action Dataset and Benchmark for Ambiguity- and Infeasibility-Aware Instruction-to-Plan Grounding
Converting natural-language instructions into executable action plans conditioned on a scene image is a core capability for embodied human-robot interaction, but existing benchmarks target English…Rate-Resolved Text Evaluation with Masked Diffusion Language Models
A single evaluation score can rank generation systems but rarely reveals what failed.The Mathematical Collective Unconscious: Jungian Archetypes within the Latent Space
Carl Jung theorised that the human psyche contains an inherited framework, the collective unconscious, populated by universal archetypes.Towards Autopilot Labeling for Short Video Content Governance
The explosive growth of short videos has presented significant challenges to content governance.Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop
Large language models can produce fluent tu- toring dialogue, but whether they actually help students learn remains unclear.bharatSetu: a 1M x 22 bridge for indic translation
India's Eighth Schedule recognises 22 languages, yet parallel data is uneven across them, and many language pairs, especially among lower-resource languages such as Bodo, Dogri, Santali and…Generalizable Model Editing Could Be More Than Direct Generalization
A central desideratum in model editing is generalization to complex tasks, which prior work formalizes under a direct generalization paradigm: treating and evaluating LLM behavior as an input-output…Preserving Updates in Low-Bit Recurrent State Quantization
Linear attention and recurrent models compress past tokens into a fixed-size state that is updated at every step.TL;QR: Querying Temporal Discursive Patterns in Textual Corpora
Many questions about large textual corpora concern patterns that unfold over time, such as a political group whose stance on a topic drifts from support to criticism over several years of debates.NepPlural: A Human-Anchored Benchmark for Persona Annotation in Nepali Migration Discourse
Pluralistic alignment asks that language models faithfully represent a society's diverse, competing values rather than collapse them into one dominant viewpoint, yet flagship pluralistic-alignment…Enhancing Zero-Shot Domain Transfer in Low-Resource Sentiment Analysis: A Case Study in Marathi
Sentiment analysis is a key task in Natural Language Processing that determines the polarity of opinions in text.Robust Marathi Sentiment Analysis using Domain-Adaptive Pre-training and Data Augmentation Approaches
For languages with limited resources, Sentiment Analysis remains a challenging problem due to limited annotated data and strong domain variability across textual sources.RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution
Recent focus in agentic reinforcement learning (RL) seeks to improve credit assignment in long-horizon tasks.Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap
Under GRPO against a frozen, reference-free LLM judge, RL exploits the judge's false positives.Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language Models
Training-free pruning removes weights from pretrained large language models to reduce their deployment cost.Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams
Large language model (LLM) agents are increasingly deployed as teams, yet they fail in characteristically social ways: information holders stay silent, dominant speakers anchor groups on wrong…