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 195
Verbalized and Internal Probabilities Are Coupled in Large Language Models
Large language models carry an internal notion of uncertainty in their sampling distribution, i.e., the probabilities they place on generating one answer rather than another.VERITYGATE: A Four-Gate Schema-Level Faithfulness Framework and Paired Benchmark for Grounded LLM Narrations over Structured Evidence
Fluent LLM explanations may not follow the evidence from a structured system.Contextual trajectory and incremental contextual displacement: Towards using LLMs to understand dynamic, utterance-specific meaning construction
Transformer-based large language models (LLMs) such as RoBERTa represent text using contextual word embeddings (CWEs), which alter the embeddings associated with each token based on surrounding…Component and Dimension Sparsity in Transformer Refusal Mechanisms
Activation steering manipulates large language model behavior by intervening on internal activations, but the mechanistic basis of these interventions remains poorly understood.Eternal Sunshine of the Spotless Mind: Systematically Erasing LLM's Memories
We consider persistent LLMs that accumulate memories of their interactions with a user over time.MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization
An assistant that serves the same user over a long horizon has to answer from what that user has revealed: which preferences still hold, which were revised, and which constraints apply now.Invariant Atoms: Sparse Coordinates of Local Semantic Geometry in Language Model Representations
Large language models often preserve meaning despite substantial changes in wording, style, and syntax, while small semantic edits can systematically alter their hidden representations.Reliable Parallel Decoding in Masked Diffusion Language Models
Masked diffusion language models (MDLMs) can generate text efficiently by predicting multiple masked tokens in parallel, but predictions from the same forward pass are not necessarily reliable when…Memory Consolidation Flattens the Temporal Shape of User Facts
Long-term memory systems turn conversations into short stored notes.Fisher-IRG: Fisher-Induced Local Invariant Representation Geometry across Language and Vision Models
Semantic-preserving transformations can induce substantial motion in learned representations, while small changes may strongly affect model predictions, raising a basic question: what local metric…FinRT: Distilling Adaptive Red-Teaming Strategies into Reusable Adversarial Generators in Consumer Finance
In regulated industries like consumer finance, seemingly harmless user queries can exploit large language model vulnerabilities, triggering safety failures and pushing responses dangerously close to…Similar Choices, Different Attention: Cross-Modal Associations in Humans and Vision-Language Models
Cross-modal associations are systematic pairings of features across modalities, such as the association of 'bouba' with round shapes and 'kiki' with sharp shapes.Large-scale factor analysis shows machine intelligence is only partially interpretable
A common assumption in language model development is that cognitive abilities are organized around a general, domain-free intelligence factor, like fluid intelligence in humans.Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
Long-horizon agents require context compression to manage growing interaction histories.Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling
Recurrent neural networks (RNNs) compress the historical context into a memory state of fixed size, thus allowing for constant-time inference.Retrieval Sensitivity to Identity Signals in Queries
Dense retrievers decide which documents reach users and the language models that use them, yet they are typically evaluated with neutral queries.When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain
Self-evolution lets large language models (LLMs) improve iteratively using their own generated data, but often suffers from self-evolution degeneration: performance improves, plateaus, then declines.DraftTrace: A Multi-View Analytics Environment for AI-Integrated Writing
Generative AI has changed how students produce writing assignments.Grounded Revision vs. Prior Injection: Probing Retrieval-Augmented Patent Claim Amendment
Retrieval-augmented generation is widely used in professional writing, yet whether retrieval grounds revision or merely injects templates is rarely tested where "correct" has a definable meaning.Long-Term Memory-Guided Enhancement for Target Perception in Audio-Language Models
Audio large language models (ALLMs) can reason about the content of audio recordings to perform complex tasks.