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 18 September 2026 to 6 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 223
HERO-MoE: Historical Expert Routing with Scale-Preserving Fusion
Mixture-of-Experts (MoE) architectures have become a standard way to scale model capacity while keeping computation sparse, yet routing remains a key determinant of MoE quality and training behavior.Retrieved but Not Delivered: Multimodal Memory Delivery for Long-Term Agents
Work on memory for multimodal agents optimizes what is written, updated and retrieved.KV-Lingo: Learning KV-Cache Translators with Distillation
Large language models represent context with a key-value (KV) cache.The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models
Large language models (LLMs) can produce factually incorrect answers with high confidence, undermining their reliability and limiting the effectiveness of uncertainty-based error detection.Does CoT-Pass@k Really Check the CoT? A Multilingual Mathematical Audit
Pass@k measures whether a model reaches a correct answer under repeated sampling, but never how: a lucky guess counts the same as sound reasoning.MixDetect: Word-Level Localization and Quantification of AI Editing
Large language models are increasingly used to edit human-written text rather than generate entire texts from scratch.ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis
Learning from experience in LLM agents has become a key paradigm for developing self-evolving agents that continuously learn and expand their capabilities.From Knowing to Abstaining: Bridging the Representation-Action Gap in Vision-Language Models
The ability of vision-language models (VLMs) to abstain from unanswerable questions is as important as their ability to answer answerable ones accurately.Distance-KV: Exploiting Relative Distance for Efficient Long-Context Inference
The memory usage and decoding latency of LLM inference grow rapidly with context length.The GUI Is Not the State: Diagnosing State Aliasing in GUI World Models
GUI World Models (GUI-WMs) are increasingly used to predict future states for agent planning and simulation, yet most existing formulations condition only on the current GUI observation and action.Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs
Extracting conditional text embeddings from large language models (LLMs) is a promising paradigm, as it requires neither additional data nor fine-tuning.IGSD: Environment-Verified Hindsight Self-Distillation for Search Agents
On-policy self-distillation densifies agent training without external teachers: a policy conditioned on privileged hindsight provides step-level guidance for its own unprivileged rollouts.Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time
In security-sensitive applications, language-model agents are often required to coordinate without disclosing confidential information.MassAlloc Attention: Let Attention Allocate Its Own Compute
FullAttn often assigns negligible normalized mass to much of the causal score space, yet dense kernels execute the complete post-score path after forming each QK tile.LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
Large Language Model (LLM) alignment is intended to ensure that models remain helpful and safe, but its stability under input distributional shift is not yet fully understood.Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Models
Existing geospatial vision-language models (Geo-VLMs) typically optimize diverse geospatial tasks through a unified multi-task adaptation paradigm without explicitly accounting for the heterogeneous…Retrospective Distillation Attribution via Normalized Response Similarity
Model distillation transfers capabilities through supervised fine-tuning (SFT) on teacher responses, often collected from commercial APIs, raising questions of model provenance.Adaptive Consistency Graph for Long-Horizon Agents
Large language model agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long sequences of dependent actions and tool calls.How Far Do Persona Effects Generalize in Language Models?
Persona prompts ask language models to answer as particular kinds of people.C-HAT-Bench: Benchmarking Chinese AI-Text Detection Beyond Fully Generated Text
Large Language Models (LLMs) increasingly participate in writing by modifying or extending human drafts, causing machine involvement to vary in both form and extent.